Probing Simile Knowledge from Pre-trained Language Models

TL;DR

This paper explores the potential of pre-trained language models to understand and generate similes by probing their embedded knowledge through a novel unified framework involving pattern-based masked sentence completion.

Contribution

It introduces a new unified framework for simile interpretation and generation by probing PLMs, utilizing pattern ensemble, search, and a secondary training process to improve prediction quality.

Findings

Effective in simile interpretation and generation tasks

Outperforms baseline models in automatic and human evaluations

Enhances prediction diversity with secondary training

Abstract

Simile interpretation (SI) and simile generation (SG) are challenging tasks for NLP because models require adequate world knowledge to produce predictions. Previous works have employed many hand-crafted resources to bring knowledge-related into models, which is time-consuming and labor-intensive. In recent years, pre-trained language models (PLMs) based approaches have become the de-facto standard in NLP since they learn generic knowledge from a large corpus. The knowledge embedded in PLMs may be useful for SI and SG tasks. Nevertheless, there are few works to explore it. In this paper, we probe simile knowledge from PLMs to solve the SI and SG tasks in the unified framework of simile triple completion for the first time. The backbone of our framework is to construct masked sentences with manual patterns and then predict the candidate words in the masked position. In this framework, we adopt a secondary training process (Adjective-Noun mask Training) with the masked language model (MLM) loss to enhance the prediction diversity of candidate words in the masked position. Moreover, pattern ensemble (PE) and pattern search (PS) are applied to improve the quality of predicted words. Finally, automatic and human evaluations demonstrate the effectiveness of our framework in both SI and SG tasks.