Can Pre-trained Language Models Interpret Similes as Smart as Human?
This addresses the under-explored task of simile interpretation in NLP, with incremental improvements for language understanding applications.
The paper tackles the problem of whether pre-trained language models (PLMs) can interpret similes by designing a Simile Property Probing task to infer shared properties, showing that PLMs underperform humans but gain 8.58% in probing and 1.37% in sentiment classification with a knowledge-enhanced method.
Simile interpretation is a crucial task in natural language processing. Nowadays, pre-trained language models (PLMs) have achieved state-of-the-art performance on many tasks. However, it remains under-explored whether PLMs can interpret similes or not. In this paper, we investigate the ability of PLMs in simile interpretation by designing a novel task named Simile Property Probing, i.e., to let the PLMs infer the shared properties of similes. We construct our simile property probing datasets from both general textual corpora and human-designed questions, containing 1,633 examples covering seven main categories. Our empirical study based on the constructed datasets shows that PLMs can infer similes' shared properties while still underperforming humans. To bridge the gap with human performance, we additionally design a knowledge-enhanced training objective by incorporating the simile knowledge into PLMs via knowledge embedding methods. Our method results in a gain of 8.58% in the probing task and 1.37% in the downstream task of sentiment classification. The datasets and code are publicly available at https://github.com/Abbey4799/PLMs-Interpret-Simile.