Cross-lingual Inference with A Chinese Entailment Graph
Tianyi Li, Sabine Weber, Mohammad Javad Hosseini, Liane Guillou, Mark Steedman
Abstract
Predicate entailment detection is a crucial task for question-answering from text, where previous work has explored unsupervised learning of entailment graphs from typed open relation triples. In this paper, we present the first pipeline for building Chinese entailment graphs, which involves a novel high-recall open relation extraction (ORE) method and the first Chinese fine-grained entity typing dataset under the FIGER type ontology. Through experiments on the Levy-Holt dataset, we verify the strength of our Chinese entailment graph, and reveal the cross-lingual complementarity: on the parallel Levy-Holt dataset, an ensemble of Chinese and English entailment graphs outperforms both monolingual graphs, and raises unsupervised SOTA by 4.7 AUC points.
BibTeX
@inproceedings{li-etal-2022-cross,
title = "Cross-lingual Inference with A {C}hinese Entailment Graph",
author = "Li, Tianyi and
Weber, Sabine and
Hosseini, Mohammad Javad and
Guillou, Liane and
Steedman, Mark",
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.96/",
doi = "10.18653/v1/2022.findings-acl.96",
pages = "1214--1233"
}