Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Niranjan Balasubramanian

MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection


Sep 16, 2021
Matthew Matero, Nikita Soni, Niranjan Balasubramanian, H. Andrew Schwartz


  Access Paper or Ask Questions

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension


Sep 14, 2021
Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui

* Accepted to EMNLP2021 Long Paper (Main Track) 

  Access Paper or Ask Questions

MuSiQue: Multi-hop Questions via Single-hop Question Composition


Aug 02, 2021
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal


  Access Paper or Ask Questions

Toward Diverse Precondition Generation


Jun 14, 2021
Heeyoung Kwon, Nathanael Chambers, Niranjan Balasubramanian


  Access Paper or Ask Questions

TellMeWhy: A Dataset for Answering Why-Questions in Narratives


Jun 11, 2021
Yash Kumar Lal, Nathanael Chambers, Raymond Mooney, Niranjan Balasubramanian

* Accepted to Findings of ACL, 2021 Data available at http://lunr.cs.stonybrook.edu/tellmewhy 

  Access Paper or Ask Questions

On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers


Jun 02, 2021
Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, Niranjan Balasubramanian


  Access Paper or Ask Questions

IrEne: Interpretable Energy Prediction for Transformers


Jun 02, 2021
Qingqing Cao, Yash Kumar Lal, Harsh Trivedi, Aruna Balasubramanian, Niranjan Balasubramanian

* ACL 2021 camera ready 

  Access Paper or Ask Questions

Bew: Towards Answering Business-Entity-Related Web Questions


Dec 10, 2020
Qingqing Cao, Oriana Riva, Aruna Balasubramanian, Niranjan Balasubramanian


  Access Paper or Ask Questions

Open4Business(O4B): An Open Access Dataset for Summarizing Business Documents


Nov 29, 2020
Amanpreet Singh, Niranjan Balasubramanian

* 7 pages, 3 figures, accepted in Workshop on Dataset Curation and Security-NeurIPS 2020 

  Access Paper or Ask Questions

Author's Sentiment Prediction


Nov 12, 2020
Mohaddeseh Bastan, Mahnaz Koupaee, Youngseo Son, Richard Sicoli, Niranjan Balasubramanian

* 12 pages, 5 figures, Accepted in COLING2020 

  Access Paper or Ask Questions

Modeling Preconditions in Text with a Crowd-sourced Dataset


Oct 14, 2020
Heeyoung Kwon, Mahnaz Koupaee, Pratyush Singh, Gargi Sawhney, Anmol Shukla, Keerthi Kumar Kallur, Nathanael Chambers, Niranjan Balasubramanian


  Access Paper or Ask Questions

Towards Accurate and Reliable Energy Measurement of NLP Models


Oct 11, 2020
Qingqing Cao, Aruna Balasubramanian, Niranjan Balasubramanian

* Accepted to SustaiNLP 2020 (co-located with EMNLP 2020) 

  Access Paper or Ask Questions

Modeling Label Semantics for Predicting Emotional Reactions


Jun 28, 2020
Radhika Gaonkar, Heeyoung Kwon, Mohaddeseh Bastan, Niranjan Balasubramanian, Nathanael Chambers

* 6 pages, 2 figures, published in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 

  Access Paper or Ask Questions

Measuring and Reducing Non-Multifact Reasoning in Multi-hop Question Answering


May 02, 2020
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal


  Access Paper or Ask Questions

DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering


May 02, 2020
Qingqing Cao, Harsh Trivedi, Aruna Balasubramanian, Niranjan Balasubramanian

* ACL 2020 camera ready 

  Access Paper or Ask Questions

Generating Narrative Text in a Switching Dynamical System


Apr 08, 2020
Noah Weber, Leena Shekhar, Heeyoung Kwon, Niranjan Balasubramanian, Nathanael Chambers


  Access Paper or Ask Questions

Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning


Nov 19, 2019
Yingru Liu, Xuewen Yang, Dongliang Xie, Xin Wang, Li Shen, Haozhi Huang, Niranjan Balasubramanian

* To appear in AAAI-2020 

  Access Paper or Ask Questions

Latent Part-of-Speech Sequences for Neural Machine Translation


Aug 30, 2019
Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian

* In proceedings of EMNLP 2019 

  Access Paper or Ask Questions

Repurposing Entailment for Multi-Hop Question Answering Tasks


Apr 20, 2019
Harsh Trivedi, Heeyoung Kwon, Tushar Khot, Ashish Sabharwal, Niranjan Balasubramanian

* Accepted at NAACL'19 

  Access Paper or Ask Questions

PoMo: Generating Entity-Specific Post-Modifiers in Context


Apr 08, 2019
Jun Seok Kang, Robert L. Logan IV, Zewei Chu, Yang Chen, Dheeru Dua, Kevin Gimpel, Sameer Singh, Niranjan Balasubramanian

* NAACL-HLT 2019 

  Access Paper or Ask Questions

Hierarchical Quantized Representations for Script Generation


Aug 28, 2018
Noah Weber, Leena Shekhar, Niranjan Balasubramanian, Nathanael Chambers

* EMNLP 2018 

  Access Paper or Ask Questions

Residualized Factor Adaptation for Community Social Media Prediction Tasks


Aug 28, 2018
Mohammadzaman Zamani, H. Andrew Schwartz, Veronica E. Lynn, Salvatore Giorgi, Niranjan Balasubramanian

* Conference on Empirical Methods in Natural Language Processing (EMNLP 2018) 

  Access Paper or Ask Questions

Fake Sentence Detection as a Training Task for Sentence Encoding


Aug 24, 2018
Viresh Ranjan, Heeyoung Kwon, Niranjan Balasubramanian, Minh Hoai


  Access Paper or Ask Questions

The Fine Line between Linguistic Generalization and Failure in Seq2Seq-Attention Models


May 08, 2018
Noah Weber, Leena Shekhar, Niranjan Balasubramanian

* Workshop on New Forms of Generalization in Deep Learning and NLP (NAACL 2018), revised to update some references 

  Access Paper or Ask Questions

Controlling Decoding for More Abstractive Summaries with Copy-Based Networks


Mar 20, 2018
Noah Weber, Leena Shekhar, Niranjan Balasubramanian, Kyunghyun Cho


  Access Paper or Ask Questions

Event Representations with Tensor-based Compositions


Nov 21, 2017
Noah Weber, Niranjan Balasubramanian, Nathanael Chambers

* Accepted at AAAI 2018 

  Access Paper or Ask Questions

MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU


Jun 03, 2017
Qingqing Cao, Niranjan Balasubramanian, Aruna Balasubramanian

* Published at 1st International Workshop on Embedded and Mobile Deep Learning colocated with MobiSys 2017 

  Access Paper or Ask Questions