no code implementations • 7 Feb 2014 • Caiming Xiong, David Johnson, Jason J. Corso
Semi-supervised clustering seeks to augment traditional clustering methods by incorporating side information provided via human expertise in order to increase the semantic meaningfulness of the resulting clusters.
no code implementations • 23 Feb 2014 • David M. Johnson, Caiming Xiong, Jason J. Corso
By introducing randomness during hierarchy training and combining the output of many of the resulting semi-random weak hierarchy metrics, we can obtain a powerful and robust nonlinear metric model.
no code implementations • CVPR 2014 • Wei Chen, Caiming Xiong, ran Xu, Jason J. Corso
Action analysis in image and video has been attracting more and more attention in computer vision.
no code implementations • 21 Oct 2014 • Ran Xu, Gang Chen, Caiming Xiong, Wei Chen, Jason J. Corso
The focus of the action understanding literature has predominately been classification, how- ever, there are many applications demanding richer action understanding such as mobile robotics and video search, with solutions to classification, localization and detection.
no code implementations • CVPR 2015 • Bruce Xiaohan Nie, Caiming Xiong, Song-Chun Zhu
Action recognition and pose estimation from video are closely related tasks for understanding human motion, most methods, however, learn separate models and combine them sequentially.
no code implementations • CVPR 2015 • Chenliang Xu, Shao-Hang Hsieh, Caiming Xiong, Jason J. Corso
There is no work we know of on simultaneously inferring actors and actions in the video, not to mention a dataset to experiment with.
11 code implementations • 4 Mar 2016 • Caiming Xiong, Stephen Merity, Richard Socher
Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering.
Ranked #4 on Visual Question Answering (VQA) on VQA v1 test-std
no code implementations • CVPR 2016 • Bo Li, Tianfu Wu, Caiming Xiong, Song-Chun Zhu
Since there are no publicly related dataset, we collect and annotate a car fluent dataset consisting of car videos with diverse fluents.
9 code implementations • 26 Sep 2016 • Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher
Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies.
8 code implementations • 5 Nov 2016 • James Bradbury, Stephen Merity, Caiming Xiong, Richard Socher
Recurrent neural networks are a powerful tool for modeling sequential data, but the dependence of each timestep's computation on the previous timestep's output limits parallelism and makes RNNs unwieldy for very long sequences.
Ranked #15 on Machine Translation on IWSLT2015 German-English
2 code implementations • EMNLP 2017 • Kazuma Hashimoto, Caiming Xiong, Yoshimasa Tsuruoka, Richard Socher
Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks.
Ranked #3 on Chunking on Penn Treebank
6 code implementations • 5 Nov 2016 • Caiming Xiong, Victor Zhong, Richard Socher
Several deep learning models have been proposed for question answering.
Ranked #2 on Open-Domain Question Answering on SQuAD1.1
no code implementations • 16 Nov 2016 • Shayne Longpre, Sabeek Pradhan, Caiming Xiong, Richard Socher
LSTMs have become a basic building block for many deep NLP models.
7 code implementations • CVPR 2017 • Jiasen Lu, Caiming Xiong, Devi Parikh, Richard Socher
The model decides whether to attend to the image and where, in order to extract meaningful information for sequential word generation.
no code implementations • 27 Apr 2017 • Chenliang Xu, Caiming Xiong, Jason J. Corso
Despite the rapid progress, existing works on action understanding focus strictly on one type of action agent, which we call actor---a human adult, ignoring the diversity of actions performed by other actors.
10 code implementations • ICLR 2018 • Romain Paulus, Caiming Xiong, Richard Socher
We introduce a neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL).
Ranked #6 on Text Summarization on CNN / Daily Mail (Anonymized)
5 code implementations • NeurIPS 2017 • Bryan McCann, James Bradbury, Caiming Xiong, Richard Socher
For fine-grained sentiment analysis and entailment, CoVe improves performance of our baseline models to the state of the art.
Ranked #9 on Text Classification on TREC-6
15 code implementations • ICLR 2018 • Victor Zhong, Caiming Xiong, Richard Socher
A significant amount of the world's knowledge is stored in relational databases.
Ranked #9 on Code Generation on WikiSQL
1 code implementation • ICLR 2018 • Caiming Xiong, Victor Zhong, Richard Socher
Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate.
Ranked #28 on Question Answering on SQuAD1.1 dev
2 code implementations • ICLR 2018 • Jiatao Gu, James Bradbury, Caiming Xiong, Victor O. K. Li, Richard Socher
Existing approaches to neural machine translation condition each output word on previously generated outputs.
Ranked #3 on Machine Translation on IWSLT2015 English-German
no code implementations • 19 Dec 2017 • Yingbo Zhou, Caiming Xiong, Richard Socher
We augment audio data through random perturbations of tempo, pitch, volume, temporal alignment, and adding random noise. We further investigate the effect of dropout when applied to the inputs of all layers of the network.
no code implementations • 19 Dec 2017 • Yingbo Zhou, Caiming Xiong, Richard Socher
However, there is usually a disparity between the negative maximum likelihood and the performance metric used in speech recognition, e. g., word error rate (WER).
Ranked #49 on Speech Recognition on LibriSpeech test-clean
no code implementations • ICLR 2018 • Huishuai Zhang, Caiming Xiong, James Bradbury, Richard Socher
Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence.
no code implementations • ICLR 2018 • Tianmin Shu, Caiming Xiong, Richard Socher
In order to help the agent learn the complex temporal dependencies necessary for the hierarchical policy, we provide it with a stochastic temporal grammar that modulates when to rely on previously learned skills and when to execute new skills.
no code implementations • ICLR 2018 • Alexander Trott, Caiming Xiong, Richard Socher
Questions that require counting a variety of objects in images remain a major challenge in visual question answering (VQA).
no code implementations • 27 Mar 2018 • Ehsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong, Richard Socher
Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources.
1 code implementation • CVPR 2018 • Luowei Zhou, Yingbo Zhou, Jason J. Corso, Richard Socher, Caiming Xiong
To address this problem, we propose an end-to-end transformer model for dense video captioning.
Ranked #11 on Video Captioning on YouCook2
2 code implementations • 19 May 2018 • Victor Zhong, Caiming Xiong, Richard Socher
Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems.
Dialogue State Tracking Multi-domain Dialogue State Tracking +1
1 code implementation • ACL 2018 • Sewon Min, Victor Zhong, Richard Socher, Caiming Xiong
Neural models for question answering (QA) over documents have achieved significant performance improvements.
Ranked #3 on Question Answering on NewsQA
no code implementations • 18 Jun 2018 • Akhilesh Gotmare, Nitish Shirish Keskar, Caiming Xiong, Richard Socher
Mode connectivity is a recently introduced frame- work that empirically establishes the connected- ness of minima by finding a high accuracy curve between two independently trained models.
5 code implementations • ICLR 2019 • Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, Richard Socher
Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting.
2 code implementations • ICLR 2019 • Ehsan Hosseini-Asl, Yingbo Zhou, Caiming Xiong, Richard Socher
In low-resource supervised setting, the results show that our approach improves absolute performance by 14% and 4% when adapting SVHN to MNIST and vice versa, respectively, which outperforms unsupervised domain adaptation methods that require high-resource unlabeled target domain.
no code implementations • ACL 2018 • Victor Zhong, Caiming Xiong, Richard Socher
Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems.
Automatic Speech Recognition (ASR) Dialogue State Tracking +3
no code implementations • EMNLP 2018 • Wojciech Kryściński, Romain Paulus, Caiming Xiong, Richard Socher
Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document.
Ranked #4 on Text Summarization on CNN / Daily Mail (Anonymized)
3 code implementations • EMNLP 2018 • Xi Victoria Lin, Richard Socher, Caiming Xiong
Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs).
no code implementations • ICLR 2019 • Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher
In particular, we prove that model generalization ability is related to the Hessian, the higher-order "smoothness" terms characterized by the Lipschitz constant of the Hessian, and the scales of the parameters.
no code implementations • 27 Sep 2018 • R. Lily Hu, Caiming Xiong, Richard Socher
We propose a model that learns to perform zero-shot classification using a meta-learner that is trained to produce a correction to the output of a previously trained learner.
no code implementations • 1 Oct 2018 • Tianmin Shu, Caiming Xiong, Ying Nian Wu, Song-Chun Zhu
In particular, the probing agent (i. e. a learner) learns to interact with the environment and with a target agent (i. e., a demonstrator) to maximize the change in the observed behaviors of that agent.
no code implementations • ICLR 2019 • Akhilesh Gotmare, Nitish Shirish Keskar, Caiming Xiong, Richard Socher
In particular, we explore knowledge distillation and learning rate heuristics of (cosine) restarts and warmup using mode connectivity and CCA.
no code implementations • CVPR 2019 • Zuxuan Wu, Caiming Xiong, Chih-Yao Ma, Richard Socher, Larry S. Davis
We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition.
1 code implementation • 8 Dec 2018 • Bo Li, Caiming Xiong, Tianfu Wu, Yu Zhou, Lun Zhang, Rufeng Chu
In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.
no code implementations • ICLR 2019 • Victor Zhong, Caiming Xiong, Nitish Shirish Keskar, Richard Socher
End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in a single document.
Ranked #5 on Question Answering on WikiHop
2 code implementations • ICLR 2019 • Chih-Yao Ma, Jiasen Lu, Zuxuan Wu, Ghassan AlRegib, Zsolt Kira, Richard Socher, Caiming Xiong
The Vision-and-Language Navigation (VLN) task entails an agent following navigational instruction in photo-realistic unknown environments.
Ranked #115 on Vision and Language Navigation on VLN Challenge
Natural Language Visual Grounding Vision and Language Navigation +2
4 code implementations • ICLR 2019 • Chien-Sheng Wu, Richard Socher, Caiming Xiong
In our model, a global memory encoder and a local memory decoder are proposed to share external knowledge.
Ranked #4 on Task-Oriented Dialogue Systems on KVRET
no code implementations • ICLR 2019 • Hao Liu, Alexander Trott, Richard Socher, Caiming Xiong
We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents.
3 code implementations • CVPR 2019 • Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira
As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making.
Ranked #115 on Vision and Language Navigation on VLN Challenge
1 code implementation • CVPR 2019 (Oral) 2019 • Chih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira
As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making.
no code implementations • ICCV 2019 • Mingfei Gao, Mingze Xu, Larry S. Davis, Richard Socher, Caiming Xiong
We propose StartNet to address Online Detection of Action Start (ODAS) where action starts and their associated categories are detected in untrimmed, streaming videos.
no code implementations • 31 Mar 2019 • Xilai Li, Yingbo Zhou, Tianfu Wu, Richard Socher, Caiming Xiong
Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks.
no code implementations • 19 Apr 2019 • Nitish Shirish Keskar, Bryan McCann, Caiming Xiong, Richard Socher
Even as pre-trained language encoders such as BERT are shared across many tasks, the output layers of question answering, text classification, and regression models are significantly different.
2 code implementations • ACL 2019 • Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, Pascale Fung
Over-dependence on domain ontology and lack of knowledge sharing across domains are two practical and yet less studied problems of dialogue state tracking.
Ranked #15 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.0
Dialogue State Tracking Multi-domain Dialogue State Tracking +2
no code implementations • ICLR 2020 • Jasdeep Singh, Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, Richard Socher
XLDA is in contrast to, and performs markedly better than, a more naive approach that aggregates examples in various languages in a way that each example is solely in one language.
Cross-Lingual Natural Language Inference Data Augmentation +3
no code implementations • 29 May 2019 • Huan Wang, Stephan Zheng, Caiming Xiong, Richard Socher
For this problem class, estimating the expected return is efficient and the trajectory can be computed deterministically given peripheral random variables, which enables us to study reparametrizable RL using supervised learning and transfer learning theory.
4 code implementations • ACL 2019 • Tao Yu, Rui Zhang, Michihiro Yasunaga, Yi Chern Tan, Xi Victoria Lin, Suyi Li, Heyang Er, Irene Li, Bo Pang, Tao Chen, Emily Ji, Shreya Dixit, David Proctor, Sungrok Shim, Jonathan Kraft, Vincent Zhang, Caiming Xiong, Richard Socher, Dragomir Radev
The best model obtains an exact match accuracy of 20. 2% over all questions and less than10% over all interaction sequences, indicating that the cross-domain setting and the con-textual phenomena of the dataset present significant challenges for future research.
no code implementations • 5 Jun 2019 • Lichao Sun, Yingbo Zhou, Ji Wang, Jia Li, Richard Sochar, Philip S. Yu, Caiming Xiong
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information.
1 code implementation • ACL 2019 • Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, Richard Socher
Deep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or reasoning over information not immediately present in the input.
Ranked #22 on Common Sense Reasoning on CommonsenseQA
no code implementations • 1 Jul 2019 • Wenling Shang, Alex Trott, Stephan Zheng, Caiming Xiong, Richard Socher
We perform a thorough ablation study to evaluate our approach on a suite of challenging maze tasks, demonstrating significant advantages from the proposed framework over baselines that lack world graph knowledge in terms of performance and efficiency.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • IJCNLP 2019 • Wojciech Kryściński, Nitish Shirish Keskar, Bryan McCann, Caiming Xiong, Richard Socher
Text summarization aims at compressing long documents into a shorter form that conveys the most important parts of the original document.
no code implementations • 31 Aug 2019 • Mingfei Gao, Larry S. Davis, Richard Socher, Caiming Xiong
We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries.
3 code implementations • IJCNLP 2019 • Rui Zhang, Tao Yu, He Yang Er, Sungrok Shim, Eric Xue, Xi Victoria Lin, Tianze Shi, Caiming Xiong, Richard Socher, Dragomir Radev
We focus on the cross-domain context-dependent text-to-SQL generation task.
Ranked #5 on Text-To-SQL on SParC
no code implementations • 7 Sep 2019 • Tong Niu, Caiming Xiong, Richard Socher
In this work, we propose a fully unsupervised model, Deleter, that is able to discover an "optimal deletion path" for an arbitrary sentence, where each intermediate sequence along the path is a coherent subsequence of the previous one.
3 code implementations • IJCNLP 2019 • Tao Yu, Rui Zhang, He Yang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, Vincent Zhang, Caiming Xiong, Richard Socher, Walter S. Lasecki, Dragomir Radev
We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems.
Ranked #8 on Dialogue State Tracking on CoSQL
7 code implementations • Preprint 2019 • Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney, Caiming Xiong, Richard Socher
Large-scale language models show promising text generation capabilities, but users cannot easily control particular aspects of the generated text.
no code implementations • 25 Sep 2019 • Wenling Shang, Alex Trott, Stephan Zheng, Caiming Xiong, Richard Socher
Efficiently learning to solve tasks in complex environments is a key challenge for reinforcement learning (RL) agents.
no code implementations • 25 Sep 2019 • Lichao Sun, Yingbo Zhou, Jia Li, Richard Socher, Philip S. Yu, Caiming Xiong
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
no code implementations • 25 Sep 2019 • Devansh Arpit, Caiming Xiong, Richard Socher
This allows deep networks trained with Entropy Penalty to generalize well even under distribution shift of spurious features.
no code implementations • 25 Sep 2019 • Hao liu, Richard Socher, Caiming Xiong
In this work, we propose a guided adaptive credit assignment method to do effectively credit assignment for policy gradient methods.
no code implementations • NeurIPS Workshop DL-IG 2020 • Peiliang Zhang, Huan Wang, Nikhil Naik, Caiming Xiong, Richard Socher
Empirically, we estimate this lower bound using a neural network to compute DIME.
2 code implementations • 1 Oct 2019 • Devansh Arpit, Caiming Xiong, Richard Socher
In this paper, we consider distribution shift as a shift in the distribution of input features during test time that exhibit low correlation with targets in the training set.
1 code implementation • Joint Conference on Lexical and Computational Semantics 2020 • Jian-Guo Zhang, Kazuma Hashimoto, Chien-Sheng Wu, Yao Wan, Philip S. Yu, Richard Socher, Caiming Xiong
Dialog state tracking (DST) is a core component in task-oriented dialog systems.
Ranked #4 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.0
dialog state tracking Multi-domain Dialogue State Tracking +1
no code implementations • 22 Oct 2019 • Ryan Theisen, Jason M. Klusowski, Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher
Classical results on the statistical complexity of linear models have commonly identified the norm of the weights $\|w\|$ as a fundamental capacity measure.
no code implementations • WS 2020 • Michael Shum, Stephan Zheng, Wojciech Kryściński, Caiming Xiong, Richard Socher
Human-like chit-chat conversation requires agents to generate responses that are fluent, engaging and consistent.
4 code implementations • EMNLP 2020 • Wojciech Kryściński, Bryan McCann, Caiming Xiong, Richard Socher
Currently used metrics for assessing summarization algorithms do not account for whether summaries are factually consistent with source documents.
no code implementations • IJCNLP 2019 • Mingfei Gao, Larry Davis, Richard Socher, Caiming Xiong
We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries.
1 code implementation • WS 2019 • Jasdeep Singh, Bryan McCann, Richard Socher, Caiming Xiong
Multilingual transfer learning can benefit both high- and low-resource languages, but the source of these improvements is not well understood.
1 code implementation • NeurIPS 2019 • Alexander Trott, Stephan Zheng, Caiming Xiong, Richard Socher
For instance, in tasks where the agent must achieve some goal state, simple distance-to-goal reward shaping often fails, as it renders learning vulnerable to local optima.
2 code implementations • ACL 2020 • Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric Lehman, Caiming Xiong, Richard Socher, Byron C. Wallace
We propose several metrics that aim to capture how well the rationales provided by models align with human rationales, and also how faithful these rationales are (i. e., the degree to which provided rationales influenced the corresponding predictions).
no code implementations • 9 Nov 2019 • Linqing Liu, Huan Wang, Jimmy Lin, Richard Socher, Caiming Xiong
Our approach is model agnostic and can be easily applied on different future teacher model architectures.
no code implementations • 18 Nov 2019 • Tong Che, Xiaofeng Liu, Site Li, Yubin Ge, Ruixiang Zhang, Caiming Xiong, Yoshua Bengio
We test the verifier network on out-of-distribution detection and adversarial example detection problems, as well as anomaly detection problems in structured prediction tasks such as image caption generation.
2 code implementations • ICLR 2020 • Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, Caiming Xiong
Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationship to the question.
Ranked #26 on Question Answering on HotpotQA
no code implementations • NeurIPS 2019 • Zuxuan Wu, Caiming Xiong, Yu-Gang Jiang, Larry S. Davis
This paper presents LiteEval, a simple yet effective coarse-to-fine framework for resource efficient video recognition, suitable for both online and offline scenarios.
1 code implementation • CVPR 2020 • Hengduo Li, Zuxuan Wu, Chen Zhu, Caiming Xiong, Richard Socher, Larry S. Davis
State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth objects.
no code implementations • 15 Jan 2020 • Peng Tang, Chetan Ramaiah, Yan Wang, ran Xu, Caiming Xiong
two-stage object detectors) by training on both labeled and unlabeled data.
1 code implementation • ICML 2020 • Víctor Campos, Alexander Trott, Caiming Xiong, Richard Socher, Xavier Giro-i-Nieto, Jordi Torres
We perform an extensive evaluation of skill discovery methods on controlled environments and show that EDL offers significant advantages, such as overcoming the coverage problem, reducing the dependence of learned skills on the initial state, and allowing the user to define a prior over which behaviors should be learned.
no code implementations • 10 Feb 2020 • Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher
We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width.
1 code implementation • 20 Feb 2020 • Devansh Arpit, Huan Wang, Caiming Xiong, Richard Socher, Yoshua Bengio
Disjoint Manifold Labeling: Neural Bayes allows us to formulate an objective which can optimally label samples from disjoint manifolds present in the support of a continuous distribution.
no code implementations • 27 Feb 2020 • Lichao Sun, Kazuma Hashimoto, Wenpeng Yin, Akari Asai, Jia Li, Philip Yu, Caiming Xiong
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously.
no code implementations • 1 Mar 2020 • Lichao Sun, Yingbo Zhou, Philip S. Yu, Caiming Xiong
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
no code implementations • 3 Mar 2020 • Junnan Li, Caiming Xiong, Richard Socher, Steven Hoi
We address the challenging problem of training object detectors with noisy annotations, where the noise contains a mixture of label noise and bounding box noise.
no code implementations • 8 Apr 2020 • Weiran Wang, Guangsen Wang, Aadyot Bhatnagar, Yingbo Zhou, Caiming Xiong, Richard Socher
For Switchboard, our phone-based BPE system achieves 6. 8\%/14. 4\% word error rate (WER) on the Switchboard/CallHome portion of the test set while joint decoding achieves 6. 3\%/13. 3\% WER.
1 code implementation • EMNLP 2020 • Chien-Sheng Wu, Steven Hoi, Richard Socher, Caiming Xiong
The underlying difference of linguistic patterns between general text and task-oriented dialogue makes existing pre-trained language models less useful in practice.
1 code implementation • EMNLP 2020 • Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King, Caiming Xiong, Steven C. H. Hoi
By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks.
2 code implementations • ACL 2020 • Nazneen Fatema Rajani, Rui Zhang, Yi Chern Tan, Stephan Zheng, Jeremy Weiss, Aadit Vyas, Abhijit Gupta, Caiming Xiong, Richard Socher, Dragomir Radev
Our framework learns to generate explanations of how the physical simulation will causally evolve so that an agent or a human can easily reason about a solution using those interpretable descriptions.
1 code implementation • ACL 2020 • Tianlu Wang, Xi Victoria Lin, Nazneen Fatema Rajani, Bryan McCann, Vicente Ordonez, Caiming Xiong
Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models.
2 code implementations • ICLR 2021 • Junnan Li, Pan Zhou, Caiming Xiong, Steven C. H. Hoi
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning.
Ranked #5 on Contrastive Learning on imagenet-1k
1 code implementation • 26 May 2020 • Yifan Gao, Chien-Sheng Wu, Shafiq Joty, Caiming Xiong, Richard Socher, Irwin King, Michael R. Lyu, Steven C. H. Hoi
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.
no code implementations • CVPR 2021 • Mingfei Gao, Yingbo Zhou, ran Xu, Richard Socher, Caiming Xiong
Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications.
Ranked #5 on Online Action Detection on THUMOS'14
1 code implementation • WS 2019 • Kazuma Hashimoto, Raffaella Buschiazzo, James Bradbury, Teresa Marshall, Richard Socher, Caiming Xiong
We build and evaluate translation models for seven target languages from English, with several different copy mechanisms and an XML-constrained beam search.
no code implementations • NeurIPS 2020 • Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher
When the trainable network is the quadratic Taylor model of a wide two-layer network, we show that neural representation can achieve improved sample complexities compared with the raw input: For learning a low-rank degree-$p$ polynomial ($p \geq 4$) in $d$ dimension, neural representation requires only $\tilde{O}(d^{\lceil p/2 \rceil})$ samples, while the best-known sample complexity upper bound for the raw input is $\tilde{O}(d^{p-1})$.
2 code implementations • ICLR 2021 • Jesse Vig, Ali Madani, Lav R. Varshney, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani
Transformer architectures have proven to learn useful representations for protein classification and generation tasks.
1 code implementation • NeurIPS 2020 • Pan Zhou, Caiming Xiong, Richard Socher, Steven C. H. Hoi
Then we propose a theory-inspired path-regularized DARTS that consists of two key modules: (i) a differential group-structured sparse binary gate introduced for each operation to avoid unfair competition among operations, and (ii) a path-depth-wise regularization used to incite search exploration for deep architectures that often converge slower than shallow ones as shown in our theory and are not well explored during the search.
1 code implementation • ACL 2020 • Yifan Gao, Chien-Sheng Wu, Shafiq Joty, Caiming Xiong, Richard Socher, Irwin King, Michael Lyu, Steven C. H. Hoi
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.
2 code implementations • NAACL 2021 • Linyong Nan, Dragomir Radev, Rui Zhang, Amrit Rau, Abhinand Sivaprasad, Chiachun Hsieh, Xiangru Tang, Aadit Vyas, Neha Verma, Pranav Krishna, Yangxiaokang Liu, Nadia Irwanto, Jessica Pan, Faiaz Rahman, Ahmad Zaidi, Mutethia Mutuma, Yasin Tarabar, Ankit Gupta, Tao Yu, Yi Chern Tan, Xi Victoria Lin, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani
Data-to-Text annotations can be a costly process, especially when dealing with tables which are the major source of structured data and contain nontrivial structures.
5 code implementations • 24 Jul 2020 • Alexander R. Fabbri, Wojciech Kryściński, Bryan McCann, Caiming Xiong, Richard Socher, Dragomir Radev
The scarcity of comprehensive up-to-date studies on evaluation metrics for text summarization and the lack of consensus regarding evaluation protocols continue to inhibit progress.
no code implementations • ACL 2020 • Jichuan Zeng, Xi Victoria Lin, Caiming Xiong, Richard Socher, Michael R. Lyu, Irwin King, Steven C. H. Hoi
Natural language interfaces to databases (NLIDB) democratize end user access to relational data.
2 code implementations • ICLR 2021 • Junnan Li, Caiming Xiong, Steven C. H. Hoi
We propose momentum prototypes (MoPro), a simple contrastive learning method that achieves online label noise correction, out-of-distribution sample removal, and representation learning.
Ranked #12 on Image Classification on OmniBenchmark (using extra training data)
no code implementations • Findings of the Association for Computational Linguistics 2020 • Congying Xia, Caiming Xiong, Philip Yu, Richard Socher
In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario.
1 code implementation • ICLR 2021 • Tao Yu, Chien-Sheng Wu, Xi Victoria Lin, Bailin Wang, Yi Chern Tan, Xinyi Yang, Dragomir Radev, Richard Socher, Caiming Xiong
We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data.
Ranked #8 on Semantic Parsing on spider
1 code implementation • EMNLP 2020 • Yifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq Joty, Steven C. H. Hoi, Caiming Xiong, Irwin King, Michael R. Lyu
Based on the learned EDU and entailment representations, we either reply to the user our final decision "yes/no/irrelevant" of the initial question, or generate a follow-up question to inquiry more information.
1 code implementation • EMNLP 2020 • Wenpeng Yin, Nazneen Fatema Rajani, Dragomir Radev, Richard Socher, Caiming Xiong
We demonstrate that this framework enables a pretrained entailment model to work well on new entailment domains in a few-shot setting, and show its effectiveness as a unified solver for several downstream NLP tasks such as question answering and coreference resolution when the end-task annotations are limited.
2 code implementations • ICLR 2021 • Junwen Bai, Weiran Wang, Yingbo Zhou, Caiming Xiong
We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations of sequence data should exhibit a simple structure in the latent space.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • NeurIPS 2020 • Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven Hoi, Weinan E
The result shows that (1) the escaping time of both SGD and ADAM~depends on the Radon measure of the basin positively and the heaviness of gradient noise negatively; (2) for the same basin, SGD enjoys smaller escaping time than ADAM, mainly because (a) the geometry adaptation in ADAM~via adaptively scaling each gradient coordinate well diminishes the anisotropic structure in gradient noise and results in larger Radon measure of a basin; (b) the exponential gradient average in ADAM~smooths its gradient and leads to lighter gradient noise tails than SGD.
no code implementations • 12 Oct 2020 • Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong
A common practice in meta-learning is to perform a train-validation split (\emph{train-val method}) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split.
no code implementations • 18 Oct 2020 • Nazneen Fatema Rajani, Ben Krause, Wengpeng Yin, Tong Niu, Richard Socher, Caiming Xiong
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens.
no code implementations • NeurIPS 2020 • Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi, Zhenhui Li, Richard Socher, Caiming Xiong
When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks.
no code implementations • EMNLP 2021 • Tong Niu, Semih Yavuz, Yingbo Zhou, Nitish Shirish Keskar, Huan Wang, Caiming Xiong
To enforce a surface form dissimilar from the input, whenever the language model emits a token contained in the source sequence, DB prevents the model from outputting the subsequent source token for the next generation step.
2 code implementations • ICLR 2021 • Shiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Rajani, Xifeng Yan, Yingbo Zhou, Caiming Xiong
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood.
Ranked #2 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1 (using extra training data)
1 code implementation • EMNLP 2020 • Jian-Guo Zhang, Kazuma Hashimoto, Wenhao Liu, Chien-Sheng Wu, Yao Wan, Philip S. Yu, Richard Socher, Caiming Xiong
Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill.
no code implementations • EMNLP 2020 • Chien-Sheng Wu, Caiming Xiong
This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Chien-Sheng Wu, Steven Hoi, Caiming Xiong
We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior.
no code implementations • 6 Nov 2020 • Hiroaki Hayashi, Wojciech Kryściński, Bryan McCann, Nazneen Rajani, Caiming Xiong
To overcome this problem, we introduce a new task of disentangled paper summarization, which seeks to generate separate summaries for the paper contributions and the context of the work, making it easier to identify the key findings shared in articles.
3 code implementations • ICCV 2021 • Junnan Li, Caiming Xiong, Steven Hoi
CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings.
no code implementations • 3 Dec 2020 • Genta Indra Winata, Guangsen Wang, Caiming Xiong, Steven Hoi
One crucial challenge of real-world multilingual speech recognition is the long-tailed distribution problem, where some resource-rich languages like English have abundant training data, but a long tail of low-resource languages have varying amounts of limited training data.
1 code implementation • 7 Dec 2020 • Govardana Sachithanandam Ramachandran, Ivan Brugere, Lav R. Varshney, Caiming Xiong
Similarly, social networks within universities and organizations may enable certain groups to more easily access people with valuable information or influence.
1 code implementation • 8 Dec 2020 • Junxian He, Wojciech Kryściński, Bryan McCann, Nazneen Rajani, Caiming Xiong
Our approach enables users to control multiple aspects of generated summaries by interacting with the summarization system through textual input in the form of a set of keywords or descriptive prompts.
no code implementations • 16 Dec 2020 • Chen Xing, Wenhao Liu, Caiming Xiong
According to recent studies and our empirical observations, one possible reason is that some easy-to-fit patterns in the training data, such as frequently co-occurring word combinations, dominate and harm pre-training, making it hard for the model to fit more complex information.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Xi Victoria Lin, Richard Socher, Caiming Xiong
We present BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing.
no code implementations • 28 Dec 2020 • Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof Geras
The early phase of training a deep neural network has a dramatic effect on the local curvature of the loss function.
1 code implementation • EMNLP 2021 • Han Guo, Nazneen Fatema Rajani, Peter Hase, Mohit Bansal, Caiming Xiong
With the availability of the fast influence functions, we demonstrate their usefulness in four applications.
no code implementations • 1 Jan 2021 • Chien-Sheng Wu, Linqing Liu, Wenhao Liu, Pontus Stenetorp, Caiming Xiong
2) A simple strategy to control the granularity of the final summary.
no code implementations • 1 Jan 2021 • Eric Zhao, Alexander R Trott, Caiming Xiong, Stephan Zheng
Policies for real-world multi-agent problems, such as optimal taxation, can be learned in multi-agent simulations with AI agents that emulate humans.
no code implementations • 1 Jan 2021 • Devansh Arpit, Aadyot Bhatnagar, Huan Wang, Caiming Xiong
Quantitatively, we show that our algorithm achieves a new state-of-the-art FID of 54. 36 on CIFAR-10, and performs competitively with existing models on CelebA in terms of FID score.
no code implementations • 1 Jan 2021 • Devansh Arpit, Huan Wang, Caiming Xiong, Richard Socher, Yoshua Bengio
Disjoint Manifold Separation: Neural Bayes allows us to formulate an objective which can optimally label samples from disjoint manifolds present in the support of a continuous distribution.
no code implementations • 1 Jan 2021 • Junnan Li, Caiming Xiong, Steven Hoi
In contrast to most existing methods, we combat noise by learning robust representation.
no code implementations • 1 Jan 2021 • Yu Bai, Tengyu Ma, Huan Wang, Caiming Xiong
In this paper, we propose Neural Rank Preserving Transforms (NRPT), a new post-calibration method that adjusts the output probabilities of a trained classifier using a calibrator of higher capacity, while maintaining its prediction accuracy.
1 code implementation • ICCV 2021 • Junnan Li, Caiming Xiong, Steven C.H. Hoi
In contrast to most existing methods, we combat noise by learning robust representation.
2 code implementations • NAACL 2021 • Karan Goel, Nazneen Rajani, Jesse Vig, Samson Tan, Jason Wu, Stephan Zheng, Caiming Xiong, Mohit Bansal, Christopher Ré
Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems.
1 code implementation • EACL 2021 • Tianxing He, Bryan McCann, Caiming Xiong, Ehsan Hosseini-Asl
In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e. g., Roberta) for natural language understanding (NLU) tasks.
no code implementations • 15 Feb 2021 • Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Modern machine learning models with high accuracy are often miscalibrated -- the predicted top probability does not reflect the actual accuracy, and tends to be over-confident.
no code implementations • 22 Feb 2021 • Rachel Luo, Aadyot Bhatnagar, Yu Bai, Shengjia Zhao, Huan Wang, Caiming Xiong, Silvio Savarese, Stefano Ermon, Edward Schmerling, Marco Pavone
In this work, we propose the local calibration error (LCE) to span the gap between average and individual reliability.
no code implementations • NeurIPS 2021 • Yu Bai, Chi Jin, Huan Wang, Caiming Xiong
Real world applications such as economics and policy making often involve solving multi-agent games with two unique features: (1) The agents are inherently asymmetric and partitioned into leaders and followers; (2) The agents have different reward functions, thus the game is general-sum.
1 code implementation • CVPR 2021 • Hanqing Wang, Wenguan Wang, Wei Liang, Caiming Xiong, Jianbing Shen
Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i. e., entailing an agent to navigate 3D environments through following linguistic instructions.
1 code implementation • 10 Mar 2021 • Govardana Sachithanandam Ramachandran, Kazuma Hashimoto, Caiming Xiong
This method gives guarantees on dialogue policy's performance and also learns to shape rewards according to intentions behind human responses, rather than just mimicking demonstration data; this couple with batch-RL helps overall with sample efficiency of the framework.
1 code implementation • 1 Apr 2021 • Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin, Neha Verma, Rui Zhang, Wojciech Kryściński, Nick Schoelkopf, Riley Kong, Xiangru Tang, Murori Mutuma, Ben Rosand, Isabel Trindade, Renusree Bandaru, Jacob Cunningham, Caiming Xiong, Dragomir Radev
Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to include questions that require complex reasoning and integration of information due to the constraint of the associated short-form answers.
1 code implementation • NAACL 2021 • Bailin Wang, Wenpeng Yin, Xi Victoria Lin, Caiming Xiong
Moreover, explicitly modeling compositions using PCFG leads to a better exploration of unseen programs, thus generate more diverse data.
no code implementations • 3 May 2021 • Congying Xia, Caiming Xiong, Philip Yu
PSN consists of two identical subnetworks with the same structure but different weights: an action network and an object network.
1 code implementation • ACL 2022 • Chien-Sheng Wu, Andrea Madotto, Wenhao Liu, Pascale Fung, Caiming Xiong
This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source.
2 code implementations • 18 May 2021 • Wojciech Kryściński, Nazneen Rajani, Divyansh Agarwal, Caiming Xiong, Dragomir Radev
The majority of available text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often contain strong layout and stylistic biases.
1 code implementation • Findings (ACL) 2021 • Chien-Sheng Wu, Linqing Liu, Wenhao Liu, Pontus Stenetorp, Caiming Xiong
In this paper, we aim to improve abstractive dialogue summarization quality and, at the same time, enable granularity control.
no code implementations • NAACL 2021 • Erik Nijkamp, Bo Pang, Ying Nian Wu, Caiming Xiong
We introduce Self-CRItic Pretraining Transformers (SCRIPT) for representation learning of text.
1 code implementation • ACL 2021 • Keyang Xu, Tongzheng Ren, Shikun Zhang, Yihao Feng, Caiming Xiong
Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs.
1 code implementation • NeurIPS 2021 • Ryan Theisen, Huan Wang, Lav R. Varshney, Caiming Xiong, Richard Socher
Moreover, we show that by varying the temperature of the learned flow models, we can generate synthetic datasets that closely resemble standard benchmark datasets, but with almost any desired Bayes error.
1 code implementation • 8 Jun 2021 • JianGuo Zhang, Kazuma Hashimoto, Yao Wan, Zhiwei Liu, Ye Liu, Caiming Xiong, Philip S. Yu
Pre-trained Transformer-based models were reported to be robust in intent classification.
no code implementations • NeurIPS 2021 • Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai
This offline result is the first that matches the sample complexity lower bound in this setting, and resolves a recent open question in offline RL.
no code implementations • NeurIPS 2021 • Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Estimating the data uncertainty in regression tasks is often done by learning a quantile function or a prediction interval of the true label conditioned on the input.
1 code implementation • 10 Jun 2021 • Eric Zhao, Alexander R. Trott, Caiming Xiong, Stephan Zheng
We study the problem of training a principal in a multi-agent general-sum game using reinforcement learning (RL).
1 code implementation • Findings (ACL) 2021 • Wenpeng Yin, Dragomir Radev, Caiming Xiong
It has been studied intensively in the past few years thanks to the availability of large-scale labeled datasets.
no code implementations • NeurIPS 2021 • Pan Zhou, Caiming Xiong, Xiao-Tong Yuan, Steven Hoi
Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic similarity between a query and its positives and negatives, and impairs performance, since some negatives are semantically similar to the query or even share the same semantic class as the query.
5 code implementations • NeurIPS 2021 • Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare, Shafiq Joty, Caiming Xiong, Steven Hoi
Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based image features) and word tokens.
Ranked #5 on Open Vocabulary Attribute Detection on OVAD-Box benchmark (using extra training data)
1 code implementation • 14 Aug 2021 • Zhiwei Liu, Yongjun Chen, Jia Li, Philip S. Yu, Julian McAuley, Caiming Xiong
In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues.
1 code implementation • ACL 2022 • Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong
We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability.
2 code implementations • 20 Sep 2021 • Aadyot Bhatnagar, Paul Kassianik, Chenghao Liu, Tian Lan, Wenzhuo Yang, Rowan Cassius, Doyen Sahoo, Devansh Arpit, Sri Subramanian, Gerald Woo, Amrita Saha, Arun Kumar Jagota, Gokulakrishnan Gopalakrishnan, Manpreet Singh, K C Krithika, Sukumar Maddineni, Daeki Cho, Bo Zong, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Steven Hoi, Huan Wang
We introduce Merlion, an open-source machine learning library for time series.
no code implementations • 23 Sep 2021 • Yongjun Chen, Jia Li, Chenghao Liu, Chenxi Li, Markus Anderle, Julian McAuley, Caiming Xiong
However, properly integrating them into user interest models is challenging since attribute dynamics can be diverse such as time-interval aware, periodic patterns (etc.
no code implementations • 29 Sep 2021 • Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
no code implementations • 29 Sep 2021 • Bo Pang, Erik Nijkamp, Wojciech Maciej Kryscinski, Silvio Savarese, Yingbo Zhou, Caiming Xiong
Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents.
1 code implementation • 8 Oct 2021 • Le Xue, Mingfei Gao, Zeyuan Chen, Caiming Xiong, ran Xu
We propose a novel framework to evaluate the robustness of transformer-based form field extraction methods via form attacks.
2 code implementations • SpaNLP (ACL) 2022 • Mingfei Gao, Zeyuan Chen, Nikhil Naik, Kazuma Hashimoto, Caiming Xiong, ran Xu
We propose a novel framework to conduct field extraction from forms with unlabeled data.
no code implementations • 11 Oct 2021 • Zahra Fatemi, Chen Xing, Wenhao Liu, Caiming Xiong
In this work, we empirically show that catastrophic forgetting occurs in such methods by evaluating them with general NLP tasks in GLUE.
1 code implementation • Findings (NAACL) 2022 • Lidiya Murakhovs'ka, Chien-Sheng Wu, Philippe Laban, Tong Niu, Wenhao Liu, Caiming Xiong
Asking good questions is an essential ability for both human and machine intelligence.
2 code implementations • ACL 2022 • Prakhar Gupta, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong
Fact-checking is an essential tool to mitigate the spread of misinformation and disinformation.
no code implementations • 19 Oct 2021 • Devansh Arpit, Aadyot Bhatnagar, Huan Wang, Caiming Xiong
Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribution.
no code implementations • 19 Oct 2021 • Anthony Meng Huat Tiong, Junnan Li, Guosheng Lin, Boyang Li, Caiming Xiong, Steven C. H. Hoi
ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the interpolative image can be used to retrieve the centroids for both source classes.
Ranked #22 on Long-tail Learning on CIFAR-10-LT (ρ=10)
no code implementations • 19 Oct 2021 • Bram Wallace, Devansh Arpit, Huan Wang, Caiming Xiong
Pretraining convolutional neural networks via self-supervision, and applying them in transfer learning, is an incredibly fast-growing field that is rapidly and iteratively improving performance across practically all image domains.
1 code implementation • 21 Oct 2021 • Devansh Arpit, Huan Wang, Yingbo Zhou, Caiming Xiong
We first show that this chaotic behavior exists even along the training optimization trajectory of a single model, and propose a simple model averaging protocol that both significantly boosts domain generalization and diminishes the impact of stochasticity by improving the rank correlation between the in-domain validation accuracy and out-domain test accuracy, which is crucial for reliable early stopping.
Ranked #4 on Domain Generalization on TerraIncognita
1 code implementation • Findings (EMNLP) 2021 • Ye Liu, Kazuma Hashimoto, Yingbo Zhou, Semih Yavuz, Caiming Xiong, Philip S. Yu
In this work, we propose Dense Hierarchical Retrieval (DHR), a hierarchical framework that can generate accurate dense representations of passages by utilizing both macroscopic semantics in the document and microscopic semantics specific to each passage.
1 code implementation • 18 Nov 2021 • Mingfei Gao, Chen Xing, Juan Carlos Niebles, Junnan Li, ran Xu, Wenhao Liu, Caiming Xiong
To enlarge the set of base classes, we propose a method to automatically generate pseudo bounding-box annotations of diverse objects from large-scale image-caption pairs.
no code implementations • 20 Nov 2021 • Wenpeng Yin, Shelby Heinecke, Jia Li, Nitish Shirish Keskar, Michael Jones, Shouzhong Shi, Stanislav Georgiev, Kurt Milich, Joseph Esposito, Caiming Xiong
The distribution gap between training datasets and data encountered in production is well acknowledged.
1 code implementation • 15 Dec 2021 • Mingfei Gao, Le Xue, Chetan Ramaiah, Chen Xing, ran Xu, Caiming Xiong
Unlike previous methods that only address a fixed set of field items, our method predicts target value for an arbitrary query based on the understanding of the layout and semantics of a form.
1 code implementation • NAACL 2022 • Alexander R. Fabbri, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong
Factual consistency is an essential quality of text summarization models in practical settings.
1 code implementation • 12 Jan 2022 • Zohreh Ovaisi, Shelby Heinecke, Jia Li, Yongfeng Zhang, Elena Zheleva, Caiming Xiong
Robust machine learning is an increasingly important topic that focuses on developing models resilient to various forms of imperfect data.
1 code implementation • 16 Jan 2022 • Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.
Ranked #1 on Task-Oriented Dialogue Systems on KVRET
6 code implementations • 28 Jan 2022 • Junnan Li, Dongxu Li, Caiming Xiong, Steven Hoi
Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision.
Ranked #3 on Open Vocabulary Attribute Detection on OVAD-Box benchmark (using extra training data)
1 code implementation • 5 Feb 2022 • Yongjun Chen, Zhiwei Liu, Jia Li, Julian McAuley, Caiming Xiong
Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering.
1 code implementation • ICLR 2022 • Yu Bai, Song Mei, Huan Wang, Yingbo Zhou, Caiming Xiong
Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly over existing approaches in several applications such as prediction intervals with improved length, minimum-volume prediction sets for multi-output regression, and label prediction sets for image classification.
2 code implementations • 28 Feb 2022 • Liang Qiu, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong
Extracting structure information from dialogue data can help us better understand user and system behaviors.
no code implementations • 15 Mar 2022 • Bo Pang, Erik Nijkamp, Wojciech Kryściński, Silvio Savarese, Yingbo Zhou, Caiming Xiong
Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents.
Ranked #1 on Text Summarization on Pubmed
no code implementations • ACL 2022 • Wenpeng Yin, Jia Li, Caiming Xiong
This work defines a new learning paradigm ConTinTin (Continual Learning from Task Instructions), in which a system should learn a sequence of new tasks one by one, each task is explained by a piece of textual instruction.
1 code implementation • 23 Mar 2022 • Tian Xie, Xinyi Yang, Angela S. Lin, Feihong Wu, Kazuma Hashimoto, Jin Qu, Young Mo Kang, Wenpeng Yin, Huan Wang, Semih Yavuz, Gang Wu, Michael Jones, Richard Socher, Yingbo Zhou, Wenhao Liu, Caiming Xiong
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
1 code implementation • 25 Mar 2022 • Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong
However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.
5 code implementations • 25 Mar 2022 • Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong
To democratize this, we train and release a family of large language models up to 16. 1B parameters, called CODEGEN, on natural language and programming language data, and open source the training library JAXFORMER.
Ranked #79 on Code Generation on HumanEval
1 code implementation • 5 Apr 2022 • Yongjun Chen, Jia Li, Caiming Xiong
A generator, as an auxiliary model, is trained jointly with the discriminator to sample plausible alternative next items and will be thrown out after training.
1 code implementation • Findings (NAACL) 2022 • Ehsan Hosseini-Asl, Wenhao Liu, Caiming Xiong
Our evaluation results on the single-task polarity prediction show that our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +4
1 code implementation • CVPR 2022 • Shu Zhang, ran Xu, Caiming Xiong, Chetan Ramaiah
Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks.
no code implementations • Findings (NAACL) 2022 • Philippe Laban, Chien-Sheng Wu, Lidiya Murakhovs'ka, Wenhao Liu, Caiming Xiong
Question generation (QGen) models are often evaluated with standardized NLG metrics that are based on n-gram overlap.
1 code implementation • 13 May 2022 • Philippe Laban, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong
Precisely assessing the progress in natural language generation (NLG) tasks is challenging, and human evaluation to establish a preference in a model's output over another is often necessary.
no code implementations • Findings (ACL) 2022 • Tong Niu, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong
When finetuned on a single rich-resource language pair, be it English-centered or not, our model is able to match the performance of the ones finetuned on all language pairs under the same data budget with less than 2. 0 points decrease in accuracy.
no code implementations • ACL 2022 • Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Nitish Shirish Keskar, Caiming Xiong
Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA.
1 code implementation • 31 May 2022 • Wenzhuo Yang, Jia Li, Caiming Xiong, Steven C. H. Hoi
Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions.
no code implementations • 6 Jun 2022 • Runyu Zhang, Qinghua Liu, Huan Wang, Caiming Xiong, Na Li, Yu Bai
Next, we show that this framework instantiated with the Optimistic Follow-The-Regularized-Leader (OFTRL) algorithm at each state (and smooth value updates) can find an $\mathcal{\widetilde{O}}(T^{-5/6})$ approximate NE in $T$ iterations, and a similar algorithm with slightly modified value update rule achieves a faster $\mathcal{\widetilde{O}}(T^{-1})$ convergence rate.