IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions

Ziheng Zeng, Kellen Cheng, Srihari Nanniyur, Jianing Zhou, Suma Bhat


Abstract
Idiomatic expression (IE) processing and comprehension have challenged pre-trained language models (PTLMs) because their meanings are non-compositional. Unlike prior works that enable IE comprehension through fine-tuning PTLMs with sentences containing IEs, in this work, we construct IEKG, a commonsense knowledge graph for figurative interpretations of IEs. This extends the established ATOMIC2020 converting PTLMs into knowledge models (KMs) that encode and infer commonsense knowledge related to IE use. Experiments show that various PTLMs can be converted into KMs with IEKG. We verify the quality of IEKG and the ability of the trained KMs with automatic and human evaluation. Through applications in natural language understanding, we show that a PTLM injected with knowledge from IEKG exhibits improved IE comprehension ability and can generalize to IEs unseen during training.
Anthology ID:
2023.emnlp-main.881
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14243–14264
Language:
URL:
https://aclanthology.org/2023.emnlp-main.881
DOI:
10.18653/v1/2023.emnlp-main.881
Bibkey:
Cite (ACL):
Ziheng Zeng, Kellen Cheng, Srihari Nanniyur, Jianing Zhou, and Suma Bhat. 2023. IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14243–14264, Singapore. Association for Computational Linguistics.
Cite (Informal):
IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions (Zeng et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.emnlp-main.881.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-1/2023.emnlp-main.881.mp4