Entity-Relation Extraction as Multi-Turn Question Answering

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1340–1350 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 1340 Entity-Relation Extraction as Multi-turn Question Answering Xiaoya Li∗♠, Fan Yin∗♠, Zijun Sun∗♦♠, Xiayu Li♠ Arianna Yuan♠,♥, Duo Chai♠, Mingxin Zhou♠ and Jiwei Li♠,♣ ♣ School of Information, Renmin University of China ♦Computer Center, Peking University ♥ Computer Science Department, Stanford University ♠ Shannon.AI {xiaoya li, fan yin, zijun sun, xiayu li, duo chai, mingxin zhou, jiwei li}@shannonai.com xfyuan@stanford.edu Abstract In this paper, we propose a new paradigm for the task of entity-relation extraction. We cast the task as a multi-turn question answering problem, i.e., the extraction of entities and re- lations is transformed to the task of identifying answer spans from the context. This multi-turn QA formalization comes with several key ad- vantages: firstly, the question query encodes important information for the entity/relation class we want to identify; secondly, QA pro- vides a natural way of jointly modeling entity and relation; and thirdly, it allows us to exploit the well developed machine reading compre- hension (MRC) models. Experiments on the ACE and the CoNLL04 corpora demonstrate that the proposed paradigm significantly outperforms previous best models. We are able to obtain the state- of-the-art results on all of the ACE04, ACE05 and CoNLL04 datasets, increasing the SOTA results on the three datasets to 49.4 (+1.0), 60.2 (+0.6) and 68.9 (+2.1), respectively. Additionally, we construct a newly developed dataset RESUME in Chinese, which requires multi-step reasoning to construct entity depen- dencies, as opposed to the single-step depen- dency extraction in the triplet exaction in pre- vious datasets. The proposed multi-turn QA model also achieves the best performance on the RESUME dataset. 1 1 Introduction Identifying entities and their relations is the pre- requisite of extracting structured knowledge from unstructured raw texts, which has recieved growing interest these years. Given a chunk of natural lan- guage text, the goal of entity-relation extraction is to transform it to a structural knowledge base. For example, given the following text: 1* indicates equal contribution. Person Corp Time Position Musk SpaceX 2002 CEO Musk Tesla 2003 CEO& product architect Musk SolarCity 2006 chairman Musk Neuralink 2016 CEO Musk The Boring Company 2016 - Table 1: An illustration of an extracted structural table. In 2002, Musk founded SpaceX, an aerospace manufacturer and space transport services Com- pany, of which he is CEO and lead designer. He helped fund Tesla, Inc., an electric vehicle and so- lar panel manufacturer, in 2003, and became its CEO and product architect. In 2006, he inspired the creation of SolarCity, a solar energy services Company, and operates as its chairman. In 2016, he co-founded Neuralink, a neurotechnology Com- pany focused on developing brain–computer in- terfaces, and is its CEO. In 2016, Musk founded The Boring Company, an infrastructure and tunnel- construction Company. We need to extract four different types of entities, i.e., Person, Company, Time and Position, and three types of relations, FOUND, FOUNDING-TIME and …

Content truncated to 500 words