Set Generation Networks for End-to-End Knowledge Base Population

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9650–9660 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 9650 Set Generation Networks for End-to-End Knowledge Base Population Dianbo Sui1,2, Chenhao Wang1,2, Yubo Chen1,2, Kang Liu1,2, Jun Zhao1,2, Wei Bi3 1 National Laboratory of Pattern Recognition, Institute of Automation, CAS 2 School of Artificial Intelligence, University of Chinese Academy of Sciences 3 Tencent AI Lab {dianbo.sui, chenhao.wang, yubo.chen, kliu, jzhao}@nlpr.ia.ac.cn Abstract The task of knowledge base population (KBP) aims to discover facts about entities from texts and expand a knowledge base with these facts. Previous studies shape end-to-end KBP as a machine translation task, which is required to convert unordered fact into a sequence accord- ing to a pre-specified order. However, the facts stated in a sentence are unordered in essence. In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts. To solve the set generation problem, we propose networks featured by transformers with non- autoregressive parallel decoding. Unlike previ- ous approaches that use an autoregressive de- coder to generate facts one by one, the pro- posed networks can directly output the final set of facts in one shot. Furthermore, to train the networks, we also design a set-based loss that forces unique predictions via bipartite match- ing. Compared with cross-entropy loss that highly penalizes small shifts in fact order, the proposed bipartite matching loss is invariant to any permutation of predictions. Benefiting from getting rid of the burden of predicting the order of multiple facts, our proposed net- works achieve state-of-the-art (SoTA) perfor- mance on two benchmark datasets. 1 Introduction Nowadays, knowledge bases (KBs) are valuable resources, which can provide back-end support for various knowledge-centric services of real-world applications, such as question answering systems (Cui et al., 2017), dialogue systems (Madotto et al., 2018) and recommendation systems (Guo et al., 2020). However, high-quality KBs still rely almost exclusively on human-curated structured or semi- structured data (Mesquita et al., 2019). Such a reliance on human curation is a major barrier to creating always-up-to-date KBs. To overcome this barrier, knowledge base popu- lation (KBP) is proposed (Ji and Grishman, 2011; Getman et al., 2018), which is a task of automat- ically discovering facts about entities from texts and expanding the incomplete KB with these facts. As shown in Table 1, a KBP system is required to take a given sentence as input and transform it into a set of facts. A fact is in the form of <h, r, t>, where h is a head entity, t is a tail entity, and r is a predicate that falls in a predefined set of predicates. Following Trisedya et al. (2019), we also assume that h and t are existing entities in the given KB while the fact <h, r, t> does not exist in the KB, since KBs typically have much better coverage on entities than on relationships. Conventionally, KBP is solved by several in- dividual components in a …

Content truncated to 500 words