Mohit Bansal

End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures

2016 · arXiv (Cornell University)

We present a novel end-to-end neural model to extract entities and relations between them. Our recurrent neural network based model captures both word sequence and dependency tree substructure information by stacking bidirectional tree-structured LSTM-RNNs on …

Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

2019 · arXiv (Cornell University)

Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble …

Continual Few-Shot Learning for Text Classification

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Natural Language Processing (NLP) is increasingly relying on general end-to-end systems that need to handle many different linguistic phenomena and nuances. For example, a Natural Language Inference (NLI) system has to recognize sentiment, handle numbers, …

Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?

2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Previous Part-Of-Speech (POS) induction models usually assume certain independence assumptions (e.g., Markov, unidirectional, local dependency) that do not hold in real languages. For example, the subject-verb agreement can be both long-term and bidirectional. To facilitate …

Debiasing Multimodal Models via Causal Information Minimization

2023 · arXiv (Cornell University)

Most existing debiasing methods for multimodal models, including causal intervention and inference methods, utilize approximate heuristics to represent the biases, such as shallow features from early stages of training or unimodal features for multimodal tasks …

Merging by Matching Models in Task Parameter Subspaces

2023 · arXiv (Cornell University)

Model merging aims to cheaply combine individual task-specific models into a single multitask model. In this work, we view past merging methods as leveraging different notions of a ''task parameter subspace'' in which models are …

On Positional Bias of Faithfulness for Long-form Summarization

2025

David Wan, Jesse Vig, Mohit Bansal, Shafiq Joty. 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.

From Paraphrase Database to Compositional Paraphrase Model and Back

2015 · Transactions of the Association for Computational Linguistics

The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, …

Charagram: Embedding Words and Sentences via Character n-grams

2016

We present CHARAGRAM embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to …

Commonsense for Generative Multi-Hop Question Answering Tasks

2018

Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multihop generative task (NarrativeQA), which requires the model …

Polite Dialogue Generation Without Parallel Data

2018 · Transactions of the Association for Computational Linguistics

Stylistic dialogue response generation, with valuable applications in personality-based conversational agents, is a challenging task because the response needs to be fluent, contextually-relevant, as well as paralinguistically accurate. Moreover, parallel datasets for regular-to-stylistic pairs are …

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

2018

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall summary. …

Combining Fact Extraction and Verification with Neural Semantic Matching Networks

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

The increasing concern with misinformation has stimulated research efforts on automatic fact checking. The recentlyreleased FEVER dataset introduced a benchmark factverification task in which a system is asked to verify a claim using evidential sentences …

أوراق هذا المؤلف