Dan Roth

EDISON: Feature Extraction for NLP, Simplified

2016

When designing Natural Language Processing (NLP) applications that use Machine Learning (ML) techniques, feature extraction becomes a significant part of the development effort, whether developing a new application or attempting to reproduce results reported for …

End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions

2018 · arXiv (Cornell University)

This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem. The premises and hypotheses in SciTail were generated with no awareness of each other, and did not specifically aim …

On the Strength of Character Language Models for Multilingual Named Entity Recognition

2018

Character-level patterns have been widely used as features in English Named Entity Recognition (NER) systems. However, to date there has been no direct investigation of the inherent differences between name and nonname tokens in text, …

TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification

2018 · arXiv (Cornell University)

Determining whether a given claim is supported by evidence is a fundamental NLP problem that is best modeled as Textual Entailment. However, given a large collection of text, finding evidence that could support or refute …

Analogous Process Structure Induction for Sub-event Sequence Prediction

2020 · arXiv (Cornell University)

Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories. Thus, …

Learning to Reason for Text Generation from Scientific Tables

2021 · arXiv (Cornell University)

In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond the surface realization …

PerKGQA: Question Answering over Personalized Knowledge Graphs

2022 · Findings of the Association for Computational Linguistics: NAACL 2022

Previous studies on question answering over knowledge graphs have typically operated over a single knowledge graph (KG). This KG is assumed to be known a priori and is leveraged similarly for all users' queries during …

Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts

2022 · arXiv (Cornell University)

Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems. However, despite the many datasets …

Label Semantic Aware Pre-training for Few-shot Text Classification

2022 · arXiv (Cornell University)

In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of label-semantics during pre-training …

Generic Temporal Reasoning with Differential Analysis and Explanation

2022 · arXiv (Cornell University)

Temporal reasoning is the task of predicting temporal relations of event pairs. While temporal reasoning models can perform reasonably well on in-domain benchmarks, we have little idea of these systems' generalizability due to existing datasets' …

Generic Temporal Reasoning with Differential Analysis and Explanation

2023

Temporal reasoning is the task of predicting temporal relations of event pairs. While temporal reasoning models can perform reasonably well on in-domain benchmarks, we have little idea of these systems’ generalizability due to existing datasets’ …

Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection

2023

In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating wh-questions that are answered by …

Zero-Shot On-the-Fly Event Schema Induction

2023

What are the events involved in a pandemic outbreak? What steps should be taken when planning a wedding? The answers to these questions can be found by collecting many documents on the complex event of …

Using LLM for Improving Key Event Discovery: Temporal-Guided News Stream Clustering with Event Summaries

2023

Understanding and characterizing the discus- sions around key events in news streams is important for analyzing political discourse. In this work, we study the problem of identification of such key events and the news articles …

H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables

2025

Nikhil Abhyankar, Vivek Gupta, Dan Roth, Chandan K. Reddy. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Towards Long Context Hallucination Detection

2025 · arXiv (Cornell University)

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, they are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context. Although many studies have investigated …

Solving General Arithmetic Word Problems

2015

This paper presents a novel approach to automatically solving arithmetic word problems. This is the first algorithmic approach that can handle arithmetic problems with multiple steps and operations, without depending on additional annotations or predefined …

Solving Hard Coreference Problems

2015

Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions. One fundamental difficulty has been that of resolving instances involving pronouns since they often require deep language understanding and use …

Cross-lingual Wikification Using Multilingual Embeddings

2016

Cross-lingual Wikification is the task of grounding mentions written in non-English documents to entries in the English Wikipedia. This task involves the problem of comparing textual clues across languages, which requires developing a notion of …

Cheap Translation for Cross-Lingual Named Entity Recognition

2017

Recent work in NLP has attempted to deal with low-resource languages but still assumed a resource level that is not present for most languages, e.g., the availability of Wikipedia in the target language. We propose …

A Structured Learning Approach to Temporal Relation Extraction

2017

Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, …

Joint Reasoning for Temporal and Causal Relations

2018

Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must occur earlier than its effect, temporal and causal relations are closely related and one relation often dictates …

Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences

2018

Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay, Dan Roth. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Two Discourse Driven Language Models for Semantics

2016

Natural language understanding often requires deep semantic knowledge. Expanding on previous proposals, we suggest that some important aspects of semantic knowledge can be modeled as a language model if done at an appropriate level of …

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

2019

Wenpeng Yin, Jamaal Hay, Dan Roth. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Cross-Lingual Ability of Multilingual BERT: An Empirical Study

2019 · arXiv (Cornell University)

Recent work has exhibited the surprising cross-lingual abilities of multilingual BERT (M-BERT) -- surprising since it is trained without any cross-lingual objective and with no aligned data. In this work, we provide a comprehensive study …

Temporal Common Sense Acquisition with Minimal Supervision

2020

Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human annotation on …

Joint Constrained Learning for Event-Event Relation Extraction

2020

Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other. In this process, one can induce event complexes that organize multi-granular events with temporal order and membership relations interweaving …

Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection

2021

Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context. To address the issue, we study contrast candidate …

Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey

2023 · ACM Computing Surveys

Large, pre-trained language models (PLMs) such as BERT and GPT have drastically changed the Natural Language Processing (NLP) field. For numerous NLP tasks, approaches leveraging PLMs have achieved state-of-the-art performance. The key idea is to …