Search Results for author:
Found 276 papers, 144 papers with code
Active Clustering with Model-Based Uncertainty Reduction
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.
Semi-Supervised Nonlinear Distance Metric Learning via Forests of Max-Margin Cluster Hierarchies
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.
Actionness Ranking with Lattice Conditional Ordinal Random Fields
Action analysis in image and video has been attracting more and more attention in computer vision.
Compositional Structure Learning for Action Understanding
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.
Joint Action Recognition and Pose Estimation From Video
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.
Can Humans Fly? Action Understanding With Multiple Classes of Actors
There is no work we know of on simultaneously inferring actors and actions in the video, not to mention a dataset to experiment with.
Dynamic Memory Networks for Visual and Textual Question Answering
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
Recognizing Car Fluents from Video
Since there are no publicly related dataset, we collect and annotate a car fluent dataset consisting of car videos with diverse fluents.
Pointer Sentinel Mixture Models
Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies.
Quasi-Recurrent Neural Networks
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
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
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
Dynamic Coattention Networks For Question Answering
Several deep learning models have been proposed for question answering.
Ranked #2 on
Open-Domain Question Answering
on SQuAD1.1
A Way out of the Odyssey: Analyzing and Combining Recent Insights for LSTMs
LSTMs have become a basic building block for many deep NLP models.
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
The model decides whether to attend to the image and where, in order to extract meaningful information for sequential word generation.
Action Understanding with Multiple Classes of Actors
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.
A Deep Reinforced Model for Abstractive Summarization
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)
Learned in Translation: Contextualized Word Vectors
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
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
A significant amount of the world's knowledge is stored in relational databases.
Ranked #9 on
Code Generation
on WikiSQL
DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
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
Non-Autoregressive Neural Machine Translation
Existing approaches to neural machine translation condition each output word on previously generated outputs.
Ranked #3 on
Machine Translation
on IWSLT2015 English-German
Improved Regularization Techniques for End-to-End Speech Recognition
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.
Improving End-to-End Speech Recognition with Policy Learning
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
Block-diagonal Hessian-free Optimization for Training Neural Networks
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.
Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning
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.
Interpretable Counting for Visual Question Answering
Questions that require counting a variety of objects in images remain a major challenge in visual question answering (VQA).
A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources.
End-to-End Dense Video Captioning with Masked Transformer
To address this problem, we propose an end-to-end transformer model for dense video captioning.
Ranked #11 on
Video Captioning
on YouCook2
Global-Locally Self-Attentive Dialogue State Tracker
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
Efficient and Robust Question Answering from Minimal Context over Documents
Neural models for question answering (QA) over documents have achieved significant performance improvements.
Ranked #3 on
Question Answering
on NewsQA
Using Mode Connectivity for Loss Landscape Analysis
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.
The Natural Language Decathlon: Multitask Learning as Question Answering
Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting.
Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation
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.
Global-Locally Self-Attentive Encoder for Dialogue State Tracking
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
Improving Abstraction in Text Summarization
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)
Multi-Hop Knowledge Graph Reasoning with Reward Shaping
Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs).
Identifying Generalization Properties in Neural Networks
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.
Correction Networks: Meta-Learning for Zero-Shot Learning
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.
Interactive Agent Modeling by Learning to Probe
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.
A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation
In particular, we explore knowledge distillation and learning rate heuristics of (cosine) restarts and warmup using mode connectivity and CCA.
AdaFrame: Adaptive Frame Selection for Fast Video Recognition
We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition.
Neural Abstract Style Transfer for Chinese Traditional Painting
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.
Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
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
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
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
Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
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
Competitive Experience Replay
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.
The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
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
The Regretful Navigation Agent for Vision-and-Language Navigation
As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making.
StartNet: Online Detection of Action Start in Untrimmed Videos
We propose StartNet to address Online Detection of Action Start (ODAS) where action starts and their associated categories are detected in untrimmed, streaming videos.
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks.
Unifying Question Answering, Text Classification, and Regression via Span Extraction
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.
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
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
XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering
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
On the Generalization Gap in Reparameterizable Reinforcement Learning
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.
SParC: Cross-Domain Semantic Parsing in Context
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.
Private Deep Learning with Teacher Ensembles
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information.
Explain Yourself! Leveraging Language Models for Commonsense Reasoning
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
Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
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
Neural Text Summarization: A Critical Evaluation
Text summarization aims at compressing long documents into a shorter form that conveys the most important parts of the original document.
WSLLN: Weakly Supervised Natural Language Localization Networks
We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries.
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
We focus on the cross-domain context-dependent text-to-SQL generation task.
Ranked #5 on
Text-To-SQL
on SParC
Deleter: Leveraging BERT to Perform Unsupervised Successive Text Compression
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.
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems.
Ranked #8 on
Dialogue State Tracking
on CoSQL
CTRL: A Conditional Transformer Language Model for Controllable Generation
Large-scale language models show promising text generation capabilities, but users cannot easily control particular aspects of the generated text.
Learning World Graph Decompositions To Accelerate Reinforcement Learning
Efficiently learning to solve tasks in complex environments is a key challenge for reinforcement learning (RL) agents.
Near-Zero-Cost Differentially Private Deep Learning with Teacher Ensembles
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
Entropy Penalty: Towards Generalization Beyond the IID Assumption
This allows deep networks trained with Entropy Penalty to generalize well even under distribution shift of spurious features.
Guided Adaptive Credit Assignment for Sample Efficient Policy Optimization
In this work, we propose a guided adaptive credit assignment method to do effectively credit assignment for policy gradient methods.
DIME: AN INFORMATION-THEORETIC DIFFICULTY MEASURE FOR AI DATASETS
Empirically, we estimate this lower bound using a neural network to compute DIME.
Predicting with High Correlation Features
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.
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking
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
Global Capacity Measures for Deep ReLU Networks via Path Sampling
Classical results on the statistical complexity of linear models have commonly identified the norm of the weights $\|w\|$ as a fundamental capacity measure.
Sketch-Fill-A-R: A Persona-Grounded Chit-Chat Generation Framework
Human-like chit-chat conversation requires agents to generate responses that are fluent, engaging and consistent.
Evaluating the Factual Consistency of Abstractive Text Summarization
Currently used metrics for assessing summarization algorithms do not account for whether summaries are factually consistent with source documents.
WSLLN:Weakly Supervised Natural Language Localization Networks
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
Multilingual transfer learning can benefit both high- and low-resource languages, but the source of these improvements is not well understood.
Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards
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.
ERASER: A Benchmark to Evaluate Rationalized NLP Models
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).
MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models
Our approach is model agnostic and can be easily applied on different future teacher model architectures.
Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
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.
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
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
LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
This paper presents LiteEval, a simple yet effective coarse-to-fine framework for resource efficient video recognition, suitable for both online and offline scenarios.
Learning from Noisy Anchors for One-stage Object Detection
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.
Proposal Learning for Semi-Supervised Object Detection
two-stage object detectors) by training on both labeled and unlabeled data.
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
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.
Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width.
Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
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.
Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously.
Differentially Private Deep Learning with Smooth Sensitivity
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
Towards Noise-resistant Object Detection with Noisy Annotations
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.
An investigation of phone-based subword units for end-to-end speech recognition
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.
TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue
The underlying difference of linguistic patterns between general text and task-oriented dialogue makes existing pre-trained language models less useful in practice.
VD-BERT: A Unified Vision and Dialog Transformer with BERT
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.
ESPRIT: Explaining Solutions to Physical Reasoning Tasks
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.
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation
Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models.
Prototypical Contrastive Learning of Unsupervised Representations
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
EMT: Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.
WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos
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
A High-Quality Multilingual Dataset for Structured Documentation Translation
We build and evaluate translation models for seven target languages from English, with several different copy mechanisms and an XML-constrained beam search.
Towards Understanding Hierarchical Learning: Benefits of Neural Representations
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 $\tilde{O}(d^{p-1})$.
BERTology Meets Biology: Interpreting Attention in Protein Language Models
Transformer architectures have proven to learn useful representations for protein classification and generation tasks.
Theory-Inspired Path-Regularized Differential Network Architecture Search
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.
Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.
DART: Open-Domain Structured Data Record to Text Generation
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.
SummEval: Re-evaluating Summarization Evaluation
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.
Photon: A Robust Cross-Domain Text-to-SQL System
Natural language interfaces to databases (NLIDB) democratize end user access to relational data.
MoPro: Webly Supervised Learning with Momentum Prototypes
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)
Composed Variational Natural Language Generation for Few-shot Intents
In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario.
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
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
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
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.
Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
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.
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
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
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
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.
How Important is the Train-Validation Split in Meta-Learning?
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.
Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens.
Online Structured Meta-learning
When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks.
Unsupervised Paraphrasing with Pretrained Language Models
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.
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
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)
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
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.
Probing Task-Oriented Dialogue Representation from Language Models
This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks.
Improving Limited Labeled Dialogue State Tracking with Self-Supervision
We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior.
What's New? Summarizing Contributions in Scientific Literature
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.
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization
CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings.
Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition
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.
GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning
Similarly, social networks within universities and organizations may enable certain groups to more easily access people with valuable information or influence.
CTRLsum: Towards Generic Controllable Text Summarization
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.
Learning from Mistakes: Using Mis-predictions as Harm Alerts in Language Pre-Training
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.
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
We present BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing.
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
The early phase of training a deep neural network has a dramatic effect on the local curvature of the loss function.
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
With the availability of the fast influence functions, we demonstrate their usefulness in four applications.
CorDial: Coarse-to-fine Abstractive Dialogue Summarization with Controllable Granularity
2) A simple strategy to control the granularity of the final summary.
ERMAS: Learning Policies Robust to Reality Gaps in Multi-Agent Simulations
Policies for real-world multi-agent problems, such as optimal taxation, can be learned in multi-agent simulations with AI agents that emulate humans.
Momentum Contrastive Autoencoder
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.
Neural Bayes: A Generic Parameterization Method for Unsupervised Learning
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.
Noise-Robust Contrastive Learning
In contrast to most existing methods, we combat noise by learning robust representation.
Improved Uncertainty Post-Calibration via Rank Preserving Transforms
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.
Learning From Noisy Data With Robust Representation Learning
In contrast to most existing methods, we combat noise by learning robust representation.
Robustness Gym: Unifying the NLP Evaluation Landscape
Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems.
Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models
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.
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
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.
Local Calibration: Metrics and Recalibration
In this work, we propose the local calibration error (LCE) to span the gap between average and individual reliability.
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
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.
Structured Scene Memory for Vision-Language Navigation
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.
Causal-aware Safe Policy Improvement for Task-oriented dialogue
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.
FeTaQA: Free-form Table Question Answering
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.
Learning to Synthesize Data for Semantic Parsing
Moreover, explicitly modeling compositions using PCFG leads to a better exploration of unseen programs, thus generate more diverse data.
Pseudo Siamese Network for Few-shot Intent Generation
PSN consists of two identical subnetworks with the same structure but different weights: an action network and an object network.
QAConv: Question Answering on Informative Conversations
This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source.
BookSum: A Collection of Datasets for Long-form Narrative Summarization
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.
Controllable Abstractive Dialogue Summarization with Sketch Supervision
In this paper, we aim to improve abstractive dialogue summarization quality and, at the same time, enable granularity control.
SCRIPT: Self-Critic PreTraining of Transformers
We introduce Self-CRItic Pretraining Transformers (SCRIPT) for representation learning of text.
Unsupervised Out-of-Domain Detection via Pre-trained Transformers
Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs.
Evaluating State-of-the-Art Classification Models Against Bayes Optimality
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.
Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection
Pre-trained Transformer-based models were reported to be robust in intent classification.
Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
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.
Understanding the Under-Coverage Bias in Uncertainty Estimation
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.
Learning to Play General-Sum Games Against Multiple Boundedly Rational Agents
We study the problem of training a principal in a multi-agent general-sum game using reinforcement learning (RL).
DocNLI: A Large-scale Dataset for Document-level Natural Language Inference
It has been studied intensively in the past few years thanks to the availability of large-scale labeled datasets.
A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning
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.
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
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)
Contrastive Self-supervised Sequential Recommendation with Robust Augmentation
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.
RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering
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.
Merlion: A Machine Learning Library for Time Series
We introduce Merlion, an open-source machine learning library for time series.
Modeling Dynamic Attributes for Next Basket Recommendation
However, properly integrating them into user interest models is challenging since attribute dynamics can be diverse such as time-interval aware, periodic patterns (etc.
Self-supervised Learning for Sequential Recommendation with Model Augmentation
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.
Long Document Summarization with Top-Down and Bottom-Up Representation Inference
Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents.
Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks
We propose a novel framework to evaluate the robustness of transformer-based form field extraction methods via form attacks.
Field Extraction from Forms with Unlabeled Data
We propose a novel framework to conduct field extraction from forms with unlabeled data.
Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting
In this work, we empirically show that catastrophic forgetting occurs in such methods by evaluating them with general NLP tasks in GLUE.
MixQG: Neural Question Generation with Mixed Answer Types
Asking good questions is an essential ability for both human and machine intelligence.
DialFact: A Benchmark for Fact-Checking in Dialogue
Fact-checking is an essential tool to mitigate the spread of misinformation and disinformation.
Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
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.
Improving Tail-Class Representation with Centroid Contrastive Learning
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)
Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles
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.
Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
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
Dense Hierarchical Retrieval for Open-Domain Question Answering
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.
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
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.
Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution
The distribution gap between training datasets and data encountered in production is well acknowledged.
Value Retrieval with Arbitrary Queries for Form-like Documents
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.
QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization
Factual consistency is an essential quality of text summarization models in practical settings.
RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems
Robust machine learning is an increasingly important topic that focuses on developing models resilient to various forms of imperfect data.
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
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
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
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)
Intent Contrastive Learning for Sequential Recommendation
Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering.
Efficient and Differentiable Conformal Prediction with General Function Classes
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.
Structure Extraction in Task-Oriented Dialogues with Slot Clustering
Extracting structure information from dialogue data can help us better understand user and system behaviors.
Long Document Summarization with Top-down and Bottom-up Inference
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
ConTinTin: Continual Learning from Task Instructions
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.
Converse: A Tree-Based Modular Task-Oriented Dialogue System
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
Improving Contrastive Learning with Model Augmentation
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.
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
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
ELECRec: Training Sequential Recommenders as Discriminators
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.
A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis
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
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework
Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks.
Quiz Design Task: Helping Teachers Create Quizzes with Automated Question Generation
Question generation (QGen) models are often evaluated with standardized NLG metrics that are based on n-gram overlap.
Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets
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.
OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval
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.
Modeling Multi-hop Question Answering as Single Sequence Prediction
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.
MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation
Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions.
Policy Optimization for Markov Games: Unified Framework and Faster Convergence
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.
