b'Dan Roth'

Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection

Despite significant progress in neural abstractive summarization, recent...
04/19/2021 ∙ by Sihao Chen, et al. ∙ 0 ∙ share

read it
ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning

Stories and narratives are composed based on a variety of events. Unders...
04/16/2021 ∙ by Rujun Han, et al. ∙ 5 ∙ share

read it
Learning to Reason for Text Generation from Scientific Tables

In this paper, we introduce SciGen, a new challenge dataset for the task...
04/16/2021 ∙ by Nafise Sadat Moosavi, et al. ∙ 0 ∙ share

read it
Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema

The Winograd Schema (WS) has been proposed as a test for measuring commo...
04/16/2021 ∙ by Yanai Elazar, et al. ∙ 0 ∙ share

read it
Paired Examples as Indirect Supervision in Latent Decision Models

Compositional, structured models are appealing because they explicitly d...
04/05/2021 ∙ by Nitish Gupta, et al. ∙ 0 ∙ share

read it
A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods

The quality of a summarization evaluation metric is quantified by calcul...
03/31/2021 ∙ by Daniel Deutsch, et al. ∙ 0 ∙ share

read it
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

A key limitation in current datasets for multi-hop reasoning is that the...
01/06/2021 ∙ by Mor Geva, et al. ∙ 0 ∙ share

read it
Coreference Reasoning in Machine Reading Comprehension

The ability to reason about multiple references to a given entity is ess...
12/31/2020 ∙ by Mingzhu Wu, et al. ∙ 2 ∙ share

read it
Unsupervised Label-aware Event Trigger and Argument Classification

Identifying events and mapping them to pre-defined event types has long ...
12/30/2020 ∙ by Hongming Zhang, et al. ∙ 0 ∙ share

read it
Learning Contextual Causality from Time-consecutive Images

Causality knowledge is crucial for many artificial intelligence systems....
12/13/2020 ∙ by Hongming Zhang, et al. ∙ 0 ∙ share

read it
What do we expect from Multiple-choice QA Systems?

The recent success of machine learning systems on various QA datasets co...
11/20/2020 ∙ by Krunal Shah, et al. ∙ 0 ∙ share

read it
Paired Representation Learning for Event and Entity Coreference

Co-reference of Events and of Entities are commonly formulated as binary...
10/24/2020 ∙ by Xiaodong Yu, et al. ∙ 0 ∙ share

read it
Temporal Reasoning on Implicit Events from Distant Supervision

Existing works on temporal reasoning among events described in text focu...
10/24/2020 ∙ by Ben Zhou, et al. ∙ 0 ∙ share

read it
Understanding the Extent to which Summarization Evaluation Metrics Measure the Information Quality of Summaries

Reference-based metrics such as ROUGE or BERTScore evaluate the content ...
10/23/2020 ∙ by Daniel Deutsch, et al. ∙ 0 ∙ share

read it
Analogous Process Structure Induction for Sub-event Sequence Prediction

Computational and cognitive studies of event understanding suggest that ...
10/16/2020 ∙ by Hongming Zhang, et al. ∙ 0 ∙ share

read it
Joint Constrained Learning for Event-Event Relation Extraction

Understanding natural language involves recognizing how multiple event m...
10/13/2020 ∙ by Haoyu Wang, et al. ∙ 0 ∙ share

read it
"What Are You Trying to Do?" Semantic Typing of Event Processes

This paper studies a new cognitively motivated semantic typing task, mul...
10/13/2020 ∙ by Muhao Chen, et al. ∙ 0 ∙ share

read it
Do Language Embeddings Capture Scales?

Pretrained Language Models (LMs) have been shown to possess significant ...
10/11/2020 ∙ by Xikun Zhang, et al. ∙ 0 ∙ share

read it
"I'd rather just go to bed": Understanding Indirect Answers

We revisit a pragmatic inference problem in dialog: understanding indire...
10/07/2020 ∙ by Annie Louis, et al. ∙ 0 ∙ share

read it
Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior

Traditional (unstructured) pruning methods for a Transformer model focus...
10/05/2020 ∙ by Zi Lin, et al. ∙ 0 ∙ share

read it
Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary

Recently, there has been growing interest in using question-answering (Q...
10/01/2020 ∙ by Daniel Deutsch, et al. ∙ 0 ∙ share

read it
Visual Pivoting for (Unsupervised) Entity Alignment

This work studies the use of visual semantic representations to align en...
09/28/2020 ∙ by Fangyu Liu, et al. ∙ 8 ∙ share

read it
Task-Oriented Dialogue as Dataflow Synthesis

We describe an approach to task-oriented dialogue in which dialogue stat...
09/24/2020 ∙ by Jacob Andreas, et al. ∙ 0 ∙ share

read it
From Spatial Relations to Spatial Configurations

Spatial Reasoning from language is essential for natural language unders...
07/19/2020 ∙ by Soham Dan, et al. ∙ 0 ∙ share

read it
Understanding Spatial Relations through Multiple Modalities

Recognizing spatial relations and reasoning about them is essential in m...
07/19/2020 ∙ by Soham Dan, et al. ∙ 4 ∙ share

read it
SacreROUGE: An Open-Source Library for Using and Developing Summarization Evaluation Metrics

We present SacreROUGE, an open-source library for using and developing s...
07/10/2020 ∙ by Daniel Deutsch, et al. ∙ 0 ∙ share

read it
Building Low-Resource NER Models Using Non-Speaker Annotation

In low-resource natural language processing (NLP), the key problem is a ...
06/17/2020 ∙ by Tatiana Tsygankova, et al. ∙ 0 ∙ share

read it
Learnability with Indirect Supervision Signals

Learning from indirect supervision signals is important in real-world AI...
06/15/2020 ∙ by Kaifu Wang, et al. ∙ 0 ∙ share

read it
Foreshadowing the Benefits of Incidental Supervision

Learning theory mostly addresses the standard learning paradigm, assumin...
06/09/2020 ∙ by Hangfeng He, et al. ∙ 19 ∙ share

read it
Incidental Supervision: Moving beyond Supervised Learning

Machine Learning and Inference methods have become ubiquitous in our att...
05/25/2020 ∙ by Dan Roth, et al. ∙ 10 ∙ share

read it
Text Classification with Few Examples using Controlled Generalization

Training data for text classification is often limited in practice, espe...
05/18/2020 ∙ by Abhijit Mahabal, et al. ∙ 0 ∙ share

read it
Context-Based Quotation Recommendation

While composing a new document, anything from a news article to an email...
05/17/2020 ∙ by Ansel MacLaughlin, et al. ∙ 0 ∙ share

read it
Temporal Common Sense Acquisition with Minimal Supervision

Temporal common sense (e.g., duration and frequency of events) is crucia...
05/08/2020 ∙ by Ben Zhou, et al. ∙ 0 ∙ share

read it
Design Challenges for Low-resource Cross-lingual Entity Linking

Cross-lingual Entity Linking (XEL) grounds mentions of entities that app...
05/02/2020 ∙ by XingYu Fu, et al. ∙ 0 ∙ share

read it
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions

A critical part of reading is being able to understand the temporal rela...
05/01/2020 ∙ by Qiang Ning, et al. ∙ 0 ∙ share

read it
TransOMCS: From Linguistic Graphs to Commonsense Knowledge

Commonsense knowledge acquisition is a key problem for artificial intell...
05/01/2020 ∙ by Hongming Zhang, et al. ∙ 16 ∙ share

read it
Cross-lingual Entity Alignment for Knowledge Graphs with Incidental Supervision from Free Text

Much research effort has been put to multilingual knowledge graph (KG) e...
05/01/2020 ∙ by Muhao Chen, et al. ∙ 2 ∙ share

read it
Extending Multilingual BERT to Low-Resource Languages

Multilingual BERT (M-BERT) has been a huge success in both supervised an...
04/28/2020 ∙ by Zihan Wang, et al. ∙ 0 ∙ share

read it
Cross-Lingual Ability of Multilingual BERT: An Empirical Study

Recent work has exhibited the surprising cross-lingual abilities of mult...
12/17/2019 ∙ by Karthikeyan K, et al. ∙ 10 ∙ share

read it
Robust Named Entity Recognition with Truecasing Pretraining

Although modern named entity recognition (NER) systems show impressive p...
12/15/2019 ∙ by Stephen Mayhew, et al. ∙ 0 ∙ share

read it
Neural Module Networks for Reasoning over Text

Answering compositional questions that require multiple steps of reasoni...
12/10/2019 ∙ by Nitish Gupta, et al. ∙ 0 ∙ share

read it
Not All Claims are Created Equal: Choosing the Right Approach to Assess Your Hypotheses

Empirical research in Natural Language Processing (NLP) has adopted a na...
11/10/2019 ∙ by Erfan Sadeqi Azer, et al. ∙ 8 ∙ share

read it
Named Entity Recognition with Partially Annotated Training Data

Supervised machine learning assumes the availability of fully-labeled da...
09/20/2019 ∙ by Stephen Mayhew, et al. ∙ 0 ∙ share

read it
"Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding

Understanding time is crucial for understanding events expressed in natu...
09/06/2019 ∙ by Ben Zhou, et al. ∙ 0 ∙ share

read it
An Improved Neural Baseline for Temporal Relation Extraction

Determining temporal relations (e.g., before or after) between events ha...
09/01/2019 ∙ by Qiang Ning, et al. ∙ 0 ∙ share

read it
Incidental Supervision from Question-Answering Signals

Human annotations are costly for many natural language processing (NLP) ...
09/01/2019 ∙ by Hangfeng He, et al. ∙ 12 ∙ share

read it
Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach

Zero-shot text classification (0Shot-TC) is a challenging NLU problem to...
08/31/2019 ∙ by Wenpeng Yin, et al. ∙ 0 ∙ share

read it
Improving Generalization in Coreference Resolution via Adversarial Training

In order for coreference resolution systems to be useful in practice, th...
08/13/2019 ∙ by Sanjay Subramanian, et al. ∙ 0 ∙ share

read it
Solving Hard Coreference Problems

Coreference resolution is a key problem in natural language understandin...
07/11/2019 ∙ by Haoruo Peng, et al. ∙ 0 ∙ share

read it
Zero-Shot Open Entity Typing as Type-Compatible Grounding

The problem of entity-typing has been studied predominantly in supervise...
07/07/2019 ∙ by Ben Zhou, et al. ∙ 0 ∙ share

read it

Dan Roth

Featured Co-authors