Improving Relation Extraction with Relational Paraphrase Sentences

Proceedings of the 28th International Conference on Computational Linguistics, pages 1687–1698 Barcelona, Spain (Online), December 8-13, 2020 1687 Improving Relation Extraction with Relational Paraphrase Sentences Junjie Yu1, Tong Zhu1, Wenliang Chen1, Wei Zhang2, Min Zhang1 Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, China1 Alibaba Group, China2 {jjyu,tzhu7}@stu.suda.edu.cn, {wlchen,minzhang}@suda.edu.cn, lantu.zw@alibaba-inc.com Abstract Supervised models for Relation Extraction (RE) typically require human-annotated training data. Due to the limited size, the human-annotated data is usually incapable of covering diverse rela- tion expressions, which could limit the performance of RE. To increase the coverage of relation expressions, we may enlarge the labeled data by hiring annotators or applying Distant Super- vision (DS). However, the human-annotated data is costly and non-scalable while the distantly supervised data contains many noises. In this paper, we propose an alternative approach to im- prove RE systems via enriching diverse expressions by relational paraphrase sentences. Based on an existing labeled data, we first automatically build a task-specific paraphrase data. Then, we propose a novel model to learn the information of diverse relation expressions. In our model, we try to capture this information on the paraphrases via a joint learning framework. Finally, we conduct experiments on a widely used dataset and the experimental results show that our approach is effective to improve the performance on relation extraction, even compared with a strong baseline. 1 Introduction Relation Extraction (RE) is an important task in Information Extraction, which identifies semantic re- lations between entities in text (Zelenko et al., 2003; Zhou et al., 2005; Mintz et al., 2009). The task becomes a typical classification problem if an entity pair in a text is given. In recent years, supervised models have achieved great progress on this task with the help of a massive amount of manually anno- tated high-quality data (Zeng et al., 2014; dos Santos et al., 2015; Miwa and Bansal, 2016; Zhang et al., 2017). However, diverse expressions for a same semantic relation are difficult to be fully covered by human- annotated data. For example, sentences (1) “Steve Jobs co-founded Apple Computer.”; (2) “Steve Jobs was the co-founder of Apple Computer.”; and (3) “Steve Jobs started Apple Computer with Wozniak.” express the same semantic relation between person “Steve Jobs” and company “Apple Computer” in different wording. Generally, it is difficult for the supervised model trained on sentence (1) and (2) to recognize the semantic relation in sentence (3). To solve the above challenge, we can use two possible solutions. The first solution is to hire annotators to label more data. While the human-annotated data is reliable, it is costly and non-scalable, with regard to both time and money. The second one is to adopt the Distant Supervision (DS) mechanism to auto- matically build a large-scale labeled data (Mintz et al., 2009). However, with the strong assumption that all sentences containing two given entities in a relation triple express the same relation, DS may result in the severe wrong labeling problem. In this paper, we use an alternative solution …

Content truncated to 500 words