IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions

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

Submission Type: Regular Long Paper

Submission Track: Semantics: Lexical

Submission Track 2: Commonsense Reasoning

Keywords: idiomatic expression, figurative semantics, commonsense knowledge, idiomatic expression comprehension, natural language understanding

TL;DR: We proposed and constructed a commonsense knowledge graph with a focus on the figurative meanings of idiomatic expressions and we show that such a graph is useful for enabling language the ability of idiomatic expression comprehension.

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 ${ATOMIC}_{20}^{20}$ 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.

Submission Number: 2212