IBERT: Idiom Cloze-style reading comprehension with Attention

Qin, Ruiyang; Luo, Haozheng; Fan, Zheheng; Ren, Ziang

doi:10.48550/arxiv.2112.02994

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the comprehension of idioms is important for many natural language processing tasks (Shao et al 2017;Liu, Pang, and Liu 2019;Qin et al 2021) ...…”

Section: Related Workmentioning

confidence: 99%

Mitigating Idiom Inconsistency: A Multi-Semantic Contrastive Learning Method for Chinese Idiom Reading Comprehension

Wu,

Hu,

Zhang

et al. 2024

AAAI

View full text Add to dashboard Cite

Chinese idioms pose a significant challenge for machine reading comprehension due to their metaphorical meanings often diverging from their literal counterparts, leading to metaphorical inconsistency. Furthermore, the same idiom can have different meanings in different contexts, resulting in contextual inconsistency. Although deep learning-based methods have achieved some success in idioms reading comprehension, existing approaches still struggle to accurately capture idiom representations due to metaphorical inconsistency and contextual inconsistency of idioms. To address these challenges, we propose a novel model, Multi-Semantic Contrastive Learning Method (MSCLM), which simultaneously addresses metaphorical inconsistency and contextual inconsistency of idioms. To mitigate metaphorical inconsistency, we propose a metaphor contrastive learning module based on the prompt method, bridging the semantic gap between literal and metaphorical meanings of idioms. To mitigate contextual inconsistency, we propose a multi-semantic cross-attention module to explore semantic features between different metaphors of the same idiom in various contexts. Our model has been compared with multiple current latest models (including GPT-3.5) on multiple Chinese idiom reading comprehension datasets, and the experimental results demonstrate that MSCLM outperforms state-of-the-art models.

show abstract

“…Although the comprehension of idioms is important for many natural language processing tasks (Shao et al 2017;Liu, Pang, and Liu 2019;Qin et al 2021) ...…”

Section: Related Workmentioning

confidence: 99%