这不是火箭科学:解释叙事中的比喻语言
It's not Rocket Science : Interpreting Figurative Language in Narratives
摘要:
比喻语言在英语中无处不在。然而,绝大多数NLP研究都集中在字面语言上。现有的文本表示设计依赖于组合性,而比喻语言往往是非组合性的。本文研究了两种非合成比喻语言(成语和明喻)的解释。我们收集了包含比喻表达的虚构叙事的数据集,以及依赖于对表达的正确解释的众包合理和不合理的延续。然后,我们训练模型来选择或生成合理的延续。我们的实验表明,完全基于预先训练的语言模型的模型在这些任务上的表现比人类差得多。我们还提出了知识增强模型,采用人类的策略来解释比喻语言类型:从上下文中推断含义,并依赖于组成词的字面意义。知识增强的模型提高了区分性和生成性任务的性能,进一步缩小了与人类性能的差距。
英文摘要:
Figurative language is ubiquitous in English. Yet, the vast majority of NLP research focuses on literal language. Existing text representations by design rely on compositionality, while figurative language is often non-compositional. In this paper, we study the interpretation of two non-compositional figurative languages (idioms and similes). We collected datasets of fictional narratives containing a figurative expression along with crowd-sourced plausible and implausible continuations relying on the correct interpretation of the expression. We then trained models to choose or generate the plausible continuation. Our experiments show that models based solely on pre-trained language models perform substantially worse than humans on these tasks. We additionally propose knowledge-enhanced models, adopting human strategies for interpreting figurative language types : inferring meaning from the context and relying on the constituent words' literal meanings. The knowledge-enhanced models improve the performance on both the discriminative and generative tasks, further bridging the gap from human performance.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。