Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

9-2021

Abstract

We study the task of learning and evaluating Chinese idiom embeddings. We first construct a new evaluation dataset that contains idiom synonyms and antonyms. Observing that existing Chinese word embedding methods may not be suitable for learning idiom embeddings, we further present a BERT-based method that directly learns embedding vectors for individual idioms. We empirically compare representative existing methods and our method. We find that our method substantially outperforms existing methods on the evaluation dataset we have constructed.

Discipline

Artificial Intelligence and Robotics | Programming Languages and Compilers

Research Areas

Data Science and Engineering

Publication

Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), Virtual Conference, September 1-3

First Page

1387

Last Page

1396

Identifier

10.26615/978-954-452-072-4_155

Publisher

Incoma Ltd.

City or Country

Virtual Conference

Share

COinS