How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?
Hailong Jin, Tiansi Dong, Lei Hou, Juanzi Li, Hui Chen, Zelin Dai, Qu Yincen
Abstract
Cross-lingual Entity Typing (CLET) aims at improving the quality of entity type prediction by transferring semantic knowledge learned from rich-resourced languages to low-resourced languages. In this paper, by utilizing multilingual transfer learning via the mixture-of-experts approach, our model dynamically capture the relationship between target language and each source language, and effectively generalize to predict types of unseen entities in new languages. Extensive experiments on multi-lingual datasets show that our method significantly outperforms multiple baselines and can robustly handle negative transfer. We questioned the relationship between language similarity and the performance of CLET. A series of experiments refute the commonsense that the more source the better, and suggest the Similarity Hypothesis for CLET.
BibTeX
@inproceedings{jin-etal-2022-cross,
title = "How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?",
author = "Jin, Hailong and
Dong, Tiansi and
Hou, Lei and
Li, Juanzi and
Chen, Hui and
Dai, Zelin and
Yincen, Qu",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.243/",
doi = "10.18653/v1/2022.findings-acl.243",
pages = "3071--3081"
}