MICE: Mining Idioms with Contextual Embeddings

TL;DR

This paper introduces MICE, a method leveraging contextual embeddings like ELMo and BERT to detect idiomatic expressions, including unseen ones, and provides a new dataset for training and evaluation.

Contribution

The paper presents a novel approach using contextual embeddings for idiom detection and introduces a new dataset, improving detection accuracy and enabling cross-lingual transfer.

Findings

Deep neural networks outperform existing methods.

Models detect unseen idioms effectively.

Cross-lingual transfer is feasible with the approach.

Abstract

Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents the development of machine learning approaches for detecting idioms, especially for expressions that do not occur in the training set. We present an approach, called MICE, that uses contextual embeddings for that purpose. We present a new dataset of multi-word expressions with literal and idiomatic meanings and use it to train a classifier based on two state-of-the-art contextual word embeddings: ELMo and BERT. We show that deep neural networks using both embeddings perform much better than existing approaches, and are capable of detecting idiomatic word use, even for expressions that were not present in the training set. We demonstrate cross-lingual transfer of developed models and analyze the size of the required dataset.