J Li, V Raheja, D Kumar, ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models, ArXiv 2023 [PDF, Code]
D Kumar, V Raheja, A Kaiser-Schatzlein, R Perry, A Joshi, J Hugues-Nuger, S Lou, N Chowdhury, Speakerly: A Voice-based Writing Assistant for Text Composition, EMNLP Industry Track 2023 [PDF, Blog]
V Raheja, D Kumar, R Koo, D Kang, CoEdIT: Text Editing by Task-Specific Instruction Tuning, EMNLP Findings 2023 [PDF, Code, Blog, Models, Data]
M Dehghan, D Kumar, L Golab, GRS: Combining Generation and Revision in Unsupervised Sentence Simplification, ACL Findings 2022 [PDF, Code]
W Du, V Raheja, D Kumar, ZM Kim, M Lopez, D Kang, Understanding Iterative Revision from Human-Written Text, ACL 2022 [PDF, Code, Blog]
W Du, ZM Kim, V Raheja, D Kumar, D Kang, Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision, In2Writing@ACL 2022 - BEST PAPER AWARD [PDF, Code, Video]
ZM Kim, W Du, V Raheja, D Kumar, D Kang, Improving iterative text revision by learning where to edit from other revision tasks, EMNLP 2022. [PDF, Code, Blog]
O Vechtomova, G Sahu, D Kumar, LyricJam: A system for generating lyrics for live instrumental music, ICCC 2021 [PDF, Website]
P Xu, D Kumar, W Yang, W Zi, K Tang, C Huang, JCK Cheung, SJD Prince, Y Cao, Optimizing Deeper Transformers on Small Datasets, ACL-IJCNLP 2021 [PDF]
S Gehrmann et al., The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics, ArXiv 2021 [PDF, ACL 2021 Workshop Page]
O Vechtomova, G Sahu, D Kumar, Generation of lyrics lines conditioned on music audio clips, NLP4MusA@ISMIR 2020. [PDF, Website, Demos, Pre-recorded talk]
D Kumar, L Mou, L Golab, O Vechtomova, Iterative edit-based unsupervised sentence simplification, ACL 2020 [PDF, Code, Pre-recorded talk]
R Cohen, R Agarwal, D Kumar, A Parmentier, TH Leung, Sensitivity to risk profiles of users when developing AI systems, Canadian AI 2020 [PDF]
R Agarwal* , D Kumar*, L Golab, S Keshav, Consentio: Managing Consent to Data Access using Permissioned Blockchains, ICBC 2020 [PDF, Code]
D Kumar, R Cohen, L Golab, Online abuse detection: the value of preprocessing and neural attention models, WASSA@NAACL-HLT 2019 [PDF, Code]
N Kushwaha, S Mehrotra, R Kalia, D Kumar, OP Vyas, Inclusion of Semantic and Time-Variant Information Using Matrix Factorization Approach for Implicit Rating of Last.Fm Dataset, Arabian Journal of Science and Engineering, 2016 [PDF, Code]
* represents equal contribution
Publications can also be found on Google Scholar