Learning and evaluating Chinese idiom embeddings

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 meth...

Full description

Saved in:

Bibliographic Details
Main Authors:	TAN, Minghuan, JIANG, Jing
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2021
Subjects:	Artificial Intelligence and Robotics Programming Languages and Compilers
Online Access:	https://ink.library.smu.edu.sg/sis_research/6723 https://ink.library.smu.edu.sg/context/sis_research/article/7726/viewcontent/2021.ranlp_main.155.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-7726
record_format	dspace
spelling	sg-smu-ink.sis_research-77262022-01-27T11:12:43Z Learning and evaluating Chinese idiom embeddings TAN, Minghuan JIANG, Jing 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. 2021-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6723 info:doi/10.26615/978-954-452-072-4_155 https://ink.library.smu.edu.sg/context/sis_research/article/7726/viewcontent/2021.ranlp_main.155.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial Intelligence and Robotics Programming Languages and Compilers
institution	Singapore Management University
building	SMU Libraries
continent	Asia
country	Singapore Singapore
content_provider	SMU Libraries
collection	InK@SMU
language	English
topic	Artificial Intelligence and Robotics Programming Languages and Compilers
spellingShingle	Artificial Intelligence and Robotics Programming Languages and Compilers TAN, Minghuan JIANG, Jing Learning and evaluating Chinese idiom embeddings
description	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.
format	text
author	TAN, Minghuan JIANG, Jing
author_facet	TAN, Minghuan JIANG, Jing
author_sort	TAN, Minghuan
title	Learning and evaluating Chinese idiom embeddings
title_short	Learning and evaluating Chinese idiom embeddings
title_full	Learning and evaluating Chinese idiom embeddings
title_fullStr	Learning and evaluating Chinese idiom embeddings
title_full_unstemmed	Learning and evaluating Chinese idiom embeddings
title_sort	learning and evaluating chinese idiom embeddings
publisher	Institutional Knowledge at Singapore Management University
publishDate	2021
url	https://ink.library.smu.edu.sg/sis_research/6723 https://ink.library.smu.edu.sg/context/sis_research/article/7726/viewcontent/2021.ranlp_main.155.pdf
_version_	1770576054406086656

Learning and evaluating Chinese idiom embeddings

Similar Items