activity
20182022
most citedMultiview Contextual Commonsense Inference: A New Dataset and Task

7 citations · 25 across the 13 of their papers we have counts for

collaborators

32 papers

cs.CL20227 cited

Multiview Contextual Commonsense Inference: A New Dataset and Task

Siqi Shen, Deepanway Ghosal, Navonil Majumder +3

Contextual commonsense inference is the task of generating various types of explanations around the events in a dyadic dialogue, including cause, motivation, emotional reaction, an…

cs.CL20221 cited

Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering

Deepanway Ghosal, Navonil Majumder, Rada Mihalcea +1

We propose a simple refactoring of multi-choice question answering (MCQA) tasks as a series of binary classifications. The MCQA task is generally performed by scoring each (questio…

cs.CL2022

WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions from Paragraphs

Hoang Thang Ta, Abu Bakar Siddiqur Rahman, Navonil Majumder +5

As free online encyclopedias with massive volumes of content, Wikipedia and Wikidata are key to many Natural Language Processing (NLP) tasks, such as information retrieval, knowled…

cs.CL20224 cited

CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues

Deepanway Ghosal, Siqi Shen, Navonil Majumder +2

This paper addresses the problem of dialogue reasoning with contextualized commonsense inference. We curate CICERO, a dataset of dyadic conversations with five types of utterance-l…

cs.CL2021

STaCK: Sentence Ordering with Temporal Commonsense Knowledge

Deepanway Ghosal, Navonil Majumder, Rada Mihalcea +1

Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document. Correctly ordering the sentences requires an understanding of cohere…

cs.CL2021

Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering

Tapas Nayak, Navonil Majumder, Soujanya Poria

Distantly supervised models are very popular for relation extraction since we can obtain a large amount of training data using the distant supervision method without human annotati…