HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection

TL;DR

This paper presents a method using pre-trained language models to accurately detect idiomatic expressions in sentences by leveraging context-aware embeddings, addressing limitations of non-contextual approaches.

Contribution

The paper introduces a novel approach employing pre-trained language models for idiom detection, improving accuracy over traditional non-contextual methods.

Findings

Pre-trained language models enhance idiom detection accuracy.

Context-aware embeddings outperform non-contextual methods.

Effective in distinguishing literal and idiomatic meanings.

Abstract

The same multi-word expressions may have different meanings in different sentences. They can be mainly divided into two categories, which are literal meaning and idiomatic meaning. Non-contextual-based methods perform poorly on this problem, and we need contextual embedding to understand the idiomatic meaning of multi-word expressions correctly. We use a pre-trained language model, which can provide a context-aware sentence embedding, to detect whether multi-word expression in the sentence is idiomatic usage.