9 citations · 28 across the 15 of their papers we have counts for
18 papers
\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments
Debanjan Ghosh, Sophia Chan
We present \llinstruct: An 8B instruction-tuned model that is designed to generate content for English Language Proficiency Assessments (ELPA) and related applications. Our work in…
Identifying Fairness Issues in Automatically Generated Testing Content
Kevin Stowe, Benny Longwill, Alyssa Francis +3
Natural language generation tools are powerful and effective for generating content. However, language models are known to display bias and fairness issues, making them impractical…
The Benefits of Label-Description Training for Zero-Shot Text Classification
Lingyu Gao, Debanjan Ghosh, Kevin Gimpel
Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific lab…
Controlled Language Generation for Language Learning Items
Kevin Stowe, Debanjan Ghosh, Mengxuan Zhao
This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of gener…
AGReE: A system for generating Automated Grammar Reading Exercises
Sophia Chan, Swapna Somasundaran, Debanjan Ghosh +1
We describe the AGReE system, which takes user-submitted passages as input and automatically generates grammar practice exercises that can be completed while reading. Multiple-choi…
"What makes a question inquisitive?" A Study on Type-Controlled Inquisitive Question Generation
Lingyu Gao, Debanjan Ghosh, Kevin Gimpel
We propose a type-controlled framework for inquisitive question generation. We annotate an inquisitive question dataset with question types, train question type classifiers, and fi…
FLUTE: Figurative Language Understanding through Textual Explanations
Tuhin Chakrabarty, Arkadiy Saakyan, Debanjan Ghosh +1
Figurative language understanding has been recently framed as a recognizing textual entailment (RTE) task (a.k.a. natural language inference, or NLI). However, similar to classical…
Figurative Language in Recognizing Textual Entailment
Tuhin Chakrabarty, Debanjan Ghosh, Adam Poliak +1
We introduce a collection of recognizing textual entailment (RTE) datasets focused on figurative language. We leverage five existing datasets annotated for a variety of figurative…
"Sharks are not the threat humans are": Argument Component Segmentation in School Student Essays
Tariq Alhindi, Debanjan Ghosh
Argument mining is often addressed by a pipeline method where segmentation of text into argumentative units is conducted first and proceeded by an argument component identification…
"Laughing at you or with you": The Role of Sarcasm in Shaping the Disagreement Space
Debanjan Ghosh, Ritvik Shrivastava, Smaranda Muresan
Detecting arguments in online interactions is useful to understand how conflicts arise and get resolved. Users often use figurative language, such as sarcasm, either as persuasive…
An Exploratory Study of Argumentative Writing by Young Students: A Transformer-based Approach
Debanjan Ghosh, Beata Beigman Klebanov, Yi Song
We present a computational exploration of argument critique writing by young students. Middle school students were asked to criticize an argument presented in the prompt, focusing…
A Report on the 2020 Sarcasm Detection Shared Task
Debanjan Ghosh, Avijit Vajpayee, Smaranda Muresan
Detecting sarcasm and verbal irony is critical for understanding people's actual sentiments and beliefs. Thus, the field of sarcasm analysis has become a popular research problem i…
Exploring Recurrent, Memory and Attention Based Architectures for Scoring Interactional Aspects of Human-Machine Text Dialog
Vikram Ramanarayanan, Matthew Mulholland, Debanjan Ghosh
An important step towards enabling English language learners to improve their conversational speaking proficiency involves automated scoring of multiple aspects of interactional co…
: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge
Tuhin Chakrabarty, Debanjan Ghosh, Smaranda Muresan +1
We propose an unsupervised approach for sarcasm generation based on a non-sarcastic input sentence. Our method employs a retrieve-and-edit framework to instantiate two major charac…
Sarcasm Analysis using Conversation Context
Debanjan Ghosh, Alexander R. Fabbri, Smaranda Muresan
Computational models for sarcasm detection have often relied on the content of utterances in isolation. However, the speaker's sarcastic intent is not always apparent without addit…
ChangeMyView Through Concessions: Do Concessions Increase Persuasion?
Elena Musi, Debanjan Ghosh, Smaranda Muresan
In discourse studies concessions are considered among those argumentative strategies that increase persuasion. We aim to empirically test this hypothesis by calculating the distrib…
"With 1 follower I must be AWESOME :P". Exploring the role of irony markers in irony recognition
Debanjan Ghosh, Smaranda Muresan
Conversations in social media often contain the use of irony or sarcasm, when the users say the opposite of what they really mean. Irony markers are the meta-communicative clues th…
The Role of Conversation Context for Sarcasm Detection in Online Interactions
Debanjan Ghosh, Alexander Richard Fabbri, Smaranda Muresan
Computational models for sarcasm detection have often relied on the content of utterances in isolation. However, speaker's sarcastic intent is not always obvious without additional…