IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions
IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions
复制标题
DOI：
10.18653/v1/2023.emnlp-main.881
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Ziheng Zeng;Kellen Tan Cheng;Srihari Venkat Nanniyur;Jianing Zhou;Suma Bhat
中科院分区：
文献类型：
--
作者：
Ziheng Zeng;Kellen Tan Cheng;Srihari Venkat Nanniyur;Jianing Zhou;Suma Bhat
惯用的表达（IE）处理和理解已经挑战了预训练的语言模型（PTLMS），因为它们的含义是非构成的。与先前的作品不同，通过用包含IES的句子进行微调的PTLM启用理解，在这项工作中，我们构建了IEKG，这是IES象征性解释的常识性知识图。这扩展了已建立的原子2020图，将PTLMS转换为编码和推断与IE使用相关的常识知识的知识模型（KMS）。实验表明，各种PTLM可以使用IEKG转换为KMS。我们通过自动和人类评估来验证IEKG的质量以及受过训练的KM的能力。通过自然语言理解的应用，我们表明，注射来自IEKG知识的PTLM具有提高的IE理解能力，并且可以在培训期间概括为IES。
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 graph, 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.