XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference

TL;DR

This paper introduces XREF, a novel entity linking model for Chinese news comments that leverages attention mechanisms and weak supervision to improve linking accuracy by utilizing article context.

Contribution

The paper presents a new attention-based model with supervised and weakly supervised training schemes for entity linking in Chinese comments, utilizing article context.

Findings

XREF outperforms previous methods on new datasets

Supervised attention loss improves model focus

Weak supervision enables training on large unlabeled data

Abstract

Automatic identification of mentioned entities in social media posts facilitates quick digestion of trending topics and popular opinions. Nonetheless, this remains a challenging task due to limited context and diverse name variations. In this paper, we study the problem of entity linking for Chinese news comments given mentions' spans. We hypothesize that comments often refer to entities in the corresponding news article, as well as topics involving the entities. We therefore propose a novel model, XREF, that leverages attention mechanisms to (1) pinpoint relevant context within comments, and (2) detect supporting entities from the news article. To improve training, we make two contributions: (a) we propose a supervised attention loss in addition to the standard cross entropy, and (b) we develop a weakly supervised training scheme to utilize the large-scale unlabeled corpus. Two new datasets in entertainment and product domains are collected and annotated for experiments. Our proposed method outperforms previous methods on both datasets.