TY - GEN
T1 - Using Commonsense Knowledge to Answer Why-Questions
AU - Lal, Yash Kumar
AU - Tandon, Niket
AU - Aggarwal, Tanvi
AU - Liu, Horace
AU - Chambers, Nathanael
AU - Mooney, Raymond
AU - Balasubramanian, Niranjan
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Answering questions in narratives about why events happened often requires commonsense knowledge external to the text. What aspects of this knowledge are available in large language models? What aspects can be made accessible via external commonsense resources? We study these questions in the context of answering questions in the TELLMEWHY dataset using COMET as a source of relevant commonsense relations. We analyze the effects of model size (T5 variants and GPT-3) along with methods of injecting knowledge (COMET) into these models. Results show that the largest models, as expected, yield substantial improvements over base models and injecting external knowledge helps models of all sizes. We also find that the format in which knowledge is provided is critical, and that smaller models benefit more from larger amounts of knowledge. Finally, we develop an ontology of knowledge types and analyze the relative coverage of the models across these categories.
AB - Answering questions in narratives about why events happened often requires commonsense knowledge external to the text. What aspects of this knowledge are available in large language models? What aspects can be made accessible via external commonsense resources? We study these questions in the context of answering questions in the TELLMEWHY dataset using COMET as a source of relevant commonsense relations. We analyze the effects of model size (T5 variants and GPT-3) along with methods of injecting knowledge (COMET) into these models. Results show that the largest models, as expected, yield substantial improvements over base models and injecting external knowledge helps models of all sizes. We also find that the format in which knowledge is provided is critical, and that smaller models benefit more from larger amounts of knowledge. Finally, we develop an ontology of knowledge types and analyze the relative coverage of the models across these categories.
UR - https://www.scopus.com/pages/publications/85149443386
U2 - 10.18653/v1/2022.emnlp-main.79
DO - 10.18653/v1/2022.emnlp-main.79
M3 - Conference contribution
AN - SCOPUS:85149443386
T3 - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
SP - 1204
EP - 1219
BT - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
A2 - Goldberg, Yoav
A2 - Kozareva, Zornitsa
A2 - Zhang, Yue
PB - Association for Computational Linguistics (ACL)
T2 - 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Y2 - 7 December 2022 through 11 December 2022
ER -