Search Results for author: Richard Socher

Found 142 papers, 68 papers with code

The Thieves on Sesame Street are Polyglots - Extracting Multilingual Models from Monolingual APIs

no code implementations EMNLP 2020 Nitish Shirish Keskar, Bryan McCann, Caiming Xiong, Richard Socher

Pre-training in natural language processing makes it easier for an adversary with only query access to a victim model to reconstruct a local copy of the victim by training with gibberish input data paired with the victim{'}s labels for that data.

Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging

no code implementations EMNLP 2020 Semih Yavuz, Kazuma Hashimoto, Wenhao Liu, Nitish Shirish Keskar, Richard Socher, Caiming Xiong

The concept of Dialogue Act (DA) is universal across different task-oriented dialogue domains - the act of {``}request{''} carries the same speaker intention whether it is for restaurant reservation or flight booking.

Data Augmentation Domain Generalization

The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning

1 code implementation5 Aug 2021 Stephan Zheng, Alexander Trott, Sunil Srinivasa, David C. Parkes, Richard Socher

Here we show that machine-learning-based economic simulation is a powerful policy and mechanism design framework to overcome these limitations.

reinforcement-learning

Evaluating State-of-the-Art Classification Models Against Bayes Optimality

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.

Neural Bayes: A Generic Parameterization Method for Unsupervised Learning

no code implementations1 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.

Representation Learning

Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing

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.

Deep Attention Semantic Parsing +1

Online Structured Meta-learning

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.

Meta-Learning

Explaining and Improving Model Behavior with k Nearest Neighbor Representations

no code implementations18 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.

Natural Language Inference

Explaining Creative Artifacts

no code implementations14 Oct 2020 Lav R. Varshney, Nazneen Fatema Rajani, Richard Socher

Human creativity is often described as the mental process of combining associative elements into a new form, but emerging computational creativity algorithms may not operate in this manner.

Text Generation Traveling Salesman Problem

Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start

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.

Coreference Resolution Natural Language Inference +1

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing

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.

Language Modelling Masked Language Modeling +2

GeDi: Generative Discriminator Guided Sequence Generation

3 code implementations Findings (EMNLP) 2021 Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann, Nitish Shirish Keskar, Shafiq Joty, Richard Socher, Nazneen Fatema Rajani

While large-scale language models (LMs) are able to imitate the distribution of natural language well enough to generate realistic text, it is difficult to control which regions of the distribution they generate.

Linguistic Acceptability Word Embeddings

Central Yup'ik and Machine Translation of Low-Resource Polysynthetic Languages

no code implementations9 Sep 2020 Christopher Liu, Laura Dominé, Kevin Chavez, Richard Socher

Machine translation tools do not yet exist for the Yup'ik language, a polysynthetic language spoken by around 8, 000 people who live primarily in Southwest Alaska.

Machine Translation Translation

SummEval: Re-evaluating Summarization Evaluation

5 code implementations24 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.

Text Summarization

Theory-Inspired Path-Regularized Differential Network Architecture Search

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.

Image Classification

BERTology Meets Biology: Interpreting Attention in Protein Language Models

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.

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

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 $\tilde{O}(d^{p-1})$.

A High-Quality Multilingual Dataset for Structured Documentation Translation

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.

Translation

CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization

no code implementations17 Jun 2020 Andre Esteva, Anuprit Kale, Romain Paulus, Kazuma Hashimoto, Wenpeng Yin, Dragomir Radev, Richard Socher

The COVID-19 global pandemic has resulted in international efforts to understand, track, and mitigate the disease, yielding a significant corpus of COVID-19 and SARS-CoV-2-related publications across scientific disciplines.

Abstractive Text Summarization Information Retrieval +2

WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos

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.

Action Detection Action Recognition +1

EMT: Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

1 code implementation26 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.

Decision Making Reading Comprehension

It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations

1 code implementation ACL 2020 Samson Tan, Shafiq Joty, Min-Yen Kan, Richard Socher

Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e. g., African American Vernacular English, Colloquial Singapore English, etc.).

ESPRIT: Explaining Solutions to Physical Reasoning 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.

The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies

2 code implementations28 Apr 2020 Stephan Zheng, Alexander Trott, Sunil Srinivasa, Nikhil Naik, Melvin Gruesbeck, David C. Parkes, Richard Socher

In experiments conducted on MTurk, an AI tax policy provides an equality-productivity trade-off that is similar to that provided by the Saez framework along with higher inverse-income weighted social welfare.

TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue

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.

Dialogue State Tracking Intent Detection +3

An investigation of phone-based subword units for end-to-end speech recognition

no code implementations8 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.

Speech Recognition

Improving out-of-distribution generalization via multi-task self-supervised pretraining

no code implementations30 Mar 2020 Isabela Albuquerque, Nikhil Naik, Junnan Li, Nitish Keskar, Richard Socher

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness.

Adversarial Robustness Domain Generalization +4

ProGen: Language Modeling for Protein Generation

2 code implementations8 Mar 2020 Ali Madani, Bryan McCann, Nikhil Naik, Nitish Shirish Keskar, Namrata Anand, Raphael R. Eguchi, Po-Ssu Huang, Richard Socher

Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science.

Language Modelling

Towards Noise-resistant Object Detection with Noisy Annotations

no code implementations3 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.

Object Detection

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning

1 code implementation20 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.

Representation Learning

Non-Autoregressive Dialog State Tracking

1 code implementation ICLR 2020 Hung Le, Richard Socher, Steven C. H. Hoi

Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself.

Dialogue State Tracking Multi-domain Dialogue State Tracking +1

Tree-structured Attention with Hierarchical Accumulation

no code implementations ICLR 2020 Xuan-Phi Nguyen, Shafiq Joty, Steven C. H. Hoi, Richard Socher

Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks.

Text Classification Translation

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width

no code implementations10 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.

Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills

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.

Limits of Detecting Text Generated by Large-Scale Language Models

no code implementations9 Feb 2020 Lav R. Varshney, Nitish Shirish Keskar, Richard Socher

Some consider large-scale language models that can generate long and coherent pieces of text as dangerous, since they may be used in misinformation campaigns.

Language Modelling Misinformation +2

Learning from Noisy Anchors for One-stage Object Detection

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.

Classification General Classification +1

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

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.

Question Answering

ERASER: A Benchmark to Evaluate Rationalized NLP Models

1 code implementation 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).

Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards

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.

WSLLN:Weakly Supervised Natural Language Localization Networks

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.

BERT is Not an Interlingua and the Bias of Tokenization

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.

Transfer Learning

Evaluating the Factual Consistency of Abstractive Text Summarization

3 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.

Abstractive Text Summarization Fact Checking +1

Global Capacity Measures for Deep ReLU Networks via Path Sampling

no code implementations22 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.

Generalization Bounds Multi-class Classification

Predicting with High Correlation Features

2 code implementations1 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.

Learning World Graph Decompositions To Accelerate Reinforcement Learning

no code implementations25 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.

reinforcement-learning

Guided Adaptive Credit Assignment for Sample Efficient Policy Optimization

no code implementations25 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.

Policy Gradient Methods

Entropy Penalty: Towards Generalization Beyond the IID Assumption

no code implementations25 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.

Near-Zero-Cost Differentially Private Deep Learning with Teacher Ensembles

no code implementations25 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.

CTRL: A Conditional Transformer Language Model for Controllable Generation

5 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.

Language Modelling Text Generation

Pretrained AI Models: Performativity, Mobility, and Change

no code implementations7 Sep 2019 Lav R. Varshney, Nitish Shirish Keskar, Richard Socher

The paradigm of pretrained deep learning models has recently emerged in artificial intelligence practice, allowing deployment in numerous societal settings with limited computational resources, but also embedding biases and enabling unintended negative uses.

Fairness

Deleter: Leveraging BERT to Perform Unsupervised Successive Text Compression

no code implementations7 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.

Language Modelling Reading Comprehension +2

WSLLN: Weakly Supervised Natural Language Localization Networks

no code implementations31 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.

Neural Text Summarization: A Critical Evaluation

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.

Text Summarization

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning

1 code implementation1 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

Explain Yourself! Leveraging Language Models for Commonsense Reasoning

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.

Common Sense Reasoning

SParC: Cross-Domain Semantic Parsing in Context

5 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.

Semantic Parsing Text-To-Sql

On the Generalization Gap in Reparameterizable Reinforcement Learning

no code implementations29 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.

Learning Theory reinforcement-learning +1

XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering

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

Unifying Question Answering, Text Classification, and Regression via Span Extraction

no code implementations19 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.

Classification General Classification +3

Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands

1 code implementation18 Apr 2019 Giovanni Campagna, Silei Xu, Mehrad Moradshahi, Richard Socher, Monica S. Lam

We advocate formalizing the capability of virtual assistants with a Virtual Assistant Programming Language (VAPL) and using a neural semantic parser to translate natural language into VAPL code.

Data Augmentation Translation

Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting

no code implementations31 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.

Continual Learning Neural Architecture Search +1

StartNet: Online Detection of Action Start in Untrimmed Videos

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.

Action Classification Frame +1

Competitive Experience Replay

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.

reinforcement-learning

Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering

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.

Question Answering

Correction Networks: Meta-Learning for Zero-Shot Learning

no code implementations27 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.

Meta-Learning Zero-Shot Learning

Identifying Generalization Properties in Neural Networks

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.

Improving Abstraction in Text Summarization

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.

Abstractive Text Summarization Language Modelling +1

Global-Locally Self-Attentive Encoder for Dialogue State Tracking

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 Dialogue State Tracking +3

Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation

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.

Speech Recognition Unsupervised Domain Adaptation

The Natural Language Decathlon: Multitask Learning as Question Answering

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.

Domain Adaptation Machine Translation +10

Using Mode Connectivity for Loss Landscape Analysis

no code implementations18 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.

Frame

Global-Locally Self-Attentive Dialogue State Tracker

2 code implementations19 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

A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation

no code implementations27 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.

Domain Adaptation Speech Recognition

Contextual Salience for Fast and Accurate Sentence Vectors

1 code implementation22 Mar 2018 Eric Zelikman, Richard Socher

We introduce contextual salience (CoSal), a measure of word importance that uses the distribution of context vectors to normalize distances and weights.

Document Summarization General Classification +2

An Analysis of Neural Language Modeling at Multiple Scales

12 code implementations22 Mar 2018 Stephen Merity, Nitish Shirish Keskar, Richard Socher

Many of the leading approaches in language modeling introduce novel, complex and specialized architectures.

Language Modelling

Interpretable Counting for Visual Question Answering

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).

Question Answering Visual Question Answering +1

Block-diagonal Hessian-free Optimization for Training Neural Networks

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.

Second-order methods

Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning

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.

reinforcement-learning

Improving Generalization Performance by Switching from Adam to SGD

6 code implementations20 Dec 2017 Nitish Shirish Keskar, Richard Socher

Concretely, we propose SWATS, a simple strategy which switches from Adam to SGD when a triggering condition is satisfied.

Language Modelling

Improving End-to-End Speech Recognition with Policy Learning

no code implementations19 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).

Speech Recognition

Improved Regularization Techniques for End-to-End Speech Recognition

no code implementations19 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.

Data Augmentation Speech Recognition

Learning when to skim and when to read

no code implementations WS 2017 Alexander Rosenberg Johansen, Richard Socher

Many recent advances in deep learning for natural language processing have come at increasing computational cost, but the power of these state-of-the-art models is not needed for every example in a dataset.

General Classification Sentiment Analysis

Weighted Transformer Network for Machine Translation

5 code implementations ICLR 2018 Karim Ahmed, Nitish Shirish Keskar, Richard Socher

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion.

Machine Translation Translation

DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

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.

Question Answering

Towards Neural Machine Translation with Latent Tree Attention

no code implementations WS 2017 James Bradbury, Richard Socher

Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing.

Machine Translation reinforcement-learning +1

Regularizing and Optimizing LSTM Language Models

47 code implementations ICLR 2018 Stephen Merity, Nitish Shirish Keskar, Richard Socher

Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering.

Language Modelling Translation

Revisiting Activation Regularization for Language RNNs

no code implementations3 Aug 2017 Stephen Merity, Bryan McCann, Richard Socher

Both of these techniques require minimal modification to existing RNN architectures and result in performance improvements comparable or superior to more complicated regularization techniques or custom cell architectures.

L2 Regularization Language Modelling

A Deep Reinforced Model for Abstractive Summarization

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).

Abstractive Text Summarization

Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning

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.

Image Captioning Language Modelling

Quasi-Recurrent Neural Networks

8 code implementations5 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.

Language Modelling Machine Translation +3

Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling

5 code implementations4 Nov 2016 Hakan Inan, Khashayar Khosravi, Richard Socher

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling.

General Classification Language Modelling

Pointer Sentinel Mixture Models

6 code implementations26 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.

Language Modelling

Dynamic Memory Networks for Visual and Textual Question Answering

11 code implementations4 Mar 2016 Caiming Xiong, Stephen Merity, Richard Socher

Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering.

Question Answering Visual Question Answering

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

13 code implementations IJCNLP 2015 Kai Sheng Tai, Richard Socher, Christopher D. Manning

Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks.

General Classification Semantic Similarity +1

Global Belief Recursive Neural Networks

no code implementations NeurIPS 2014 Romain Paulus, Richard Socher, Christopher D. Manning

Recursive Neural Networks have recently obtained state of the art performance on several natural language processing tasks.

Sentiment Analysis

Grounded Compositional Semantics for Finding and Describing Images with Sentences

no code implementations TACL 2014 Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning, Andrew Y. Ng

Previous work on Recursive Neural Networks (RNNs) shows that these models can produce compositional feature vectors for accurately representing and classifying sentences or images.

Reasoning With Neural Tensor Networks for Knowledge Base Completion

no code implementations NeurIPS 2013 Richard Socher, Danqi Chen, Christopher D. Manning, Andrew Ng

We assess the model by considering the problem of predicting additional true relations between entities given a partial knowledge base.

Knowledge Base Completion Tensor Networks

Cannot find the paper you are looking for? You can Submit a new open access paper.