Cross-lingual Inference with A Chinese Entailment Graph

Anonymous

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 and a boolean QA task, 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 beats both monolinguals, and raises unsupervised SOTA by 4.7 AUC points.

Paper Type: long