Published in EMNLP 2020, 2020
In this paper my focussed contribution was developing the V2CQA approach to improve captioning.
Recommended citation: Tejas Gokhale, Pratyay Banerjee, Chitta Baral and Yezhou Yang (2020, March). MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering. EMNLP 2020. https://arxiv.org/abs/2009.
Published in EMNLP 2020, 2020
In this paper I formulate a new framework to perform zero-shot question answering over unstructured and structured knowledge bases.
Recommended citation: Pratyay Banerjee and Chitta Baral (2020, May). Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering. CoRR, arxiv.org. https://arxiv.org/abs/2005.00316
Published in arxiv.org, 2020
In this paper I created a new synthetic dataset to improve SKR and a new QA model approach for MCQA achieving SOTA on OBQA and QASC datasets.
Recommended citation: Pratyay Banerjee and Chitta Baral (2020, March). Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering. CoRR, arxiv.org. https://arxiv.org/abs/2004.03101
Published in arxiv.org, 2020
In this paper we survey different kinds of techniques to incorporate additional knowledge.
Recommended citation: Chitta Baral, Pratyay Banerjee, Kuntal Kumar Pal and Arindam Mitra (2020, March). Natural Language QA Approaches using Reasoning with External Knowledge . CoRR, arxiv.org. https://arxiv.org/abs/2003.03446
Published in EMNLP 2020, 2020
In this paper my focussed contribution was developing the V2CQA approach to improve captioning.
Recommended citation: Zhiyuan Fang, Tejas Gokhale, Pratyay Banerjee, Chitta Baral and Yezhou Yang (2020, March). Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning. CoRR, arxiv.org. https://arxiv.org/abs/2003.05162
Published in 16th European Conference on Computer Vision (ECCV 2020), 2020
In this paper I explore ways to make VQA models robust to Logical Questions
Recommended citation: Tejas Gokhale, Pratyay Banerjee, Chitta Baral and Yezhou Yang (2020, February). VQA-LOL: Visual Question Answering under the Lens of Logic. 16th European Conference on Computer Vision (ECCV 2020) https://arxiv.org/abs/2002.08325
Published in arxiv.org, 2019
In this paper I explore ways to use external knowledge to improve Named Entity Recognition in BioMedical texts.
Recommended citation: Pratyay Banerjee, Kuntal Kumar Pal, Murthy Devarakonda and Chitta Baral (2019, November). Knowledge Guided Named Entity Recognition. CoRR, arxiv.org. https://arxiv.org/abs/1911.03869
Published in Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), 2019
In this paper I explore ways te regenerate explanations given a question and correct answer.
Recommended citation: Banerjee, P. (2019, Septemeber). ASU at TextGraphs 2019 Shared Task: Explanation ReGeneration using Language Models and Iterative Re-Ranking. In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13). https://www.aclweb.org/anthology/D19-5310/
Published in arxiv.org, 2019
In this paper we evaluate multiple ways to incorporate knowledge in large Neural Language Models.
Recommended citation: Mitra, A., Banerjee, P., Pal, K. K., Mishra S. & Baral, C. (2019, July). Exploring ways to incorporate additional knowledge to improve Natural Language Commonsense Question Answering. CoRR, arxiv.org https://arxiv.org/abs/1909.08855
Published in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 6120-6129), 2019
In this paper we try to solve OpenBookQA from AllenAI using multiple new techniques.
Recommended citation: Banerjee, P., Pal, K. K., Mitra, A., & Baral, C. (2019, July). Careful Selection of Knowledge to Solve Open Book Question Answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 6120-6129). https://www.aclweb.org/anthology/P19-1615/