Dynamic Topic Tracker for KB-to-Text Generation

Proceedings of the 28th International Conference on Computational Linguistics, pages 2369–2380 Barcelona, Spain (Online), December 8-13, 2020 2369 Dynamic Topic Tracker for KB-to-Text Generation∗ Zihao Fu1, Lidong Bing2, Wai Lam1, Shoaib Jameel3 1Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong 2DAMO Academy, Alibaba Group 3School of Computer Science and Electronic Engineering, University of Essex zhfu@se.cuhk.edu.hk; l.bing@alibaba-inc.com; wlam@se.cuhk.edu.hk; shoaib.jameel@essex.ac.uk Abstract Recently, many KB-to-text generation tasks have been proposed to bridge the gap between knowledge bases and natural language by directly converting a group of knowledge base triples into human-readable sentences. However, most of the existing models suffer from the off-topic problem, namely, the models are prone to generate some unrelated clauses that are somehow involved with certain input terms regardless of the given input data. This problem seriously de- grades the quality of the generation results. In this paper, we propose a novel dynamic topic tracker for solving this problem. Different from existing models, our proposed model learns a global hidden representation for topics and recognizes the corresponding topic during each generation step. The recognized topic is used as additional information to guide the generation process and thus alleviates the off-topic problem. The experimental results show that our pro- posed model can enhance the performance of sentence generation and the off-topic problem is significantly mitigated. 1 Introduction In recent years, many knowledge bases (KBs) have been built to incorporate different kinds of human knowledge into a structured triple representation such as Freebase (Bollacker et al., 2008), DBpedia (Auer et al., 2007), YAGO (Suchanek et al., 2007) and Wikidata (Vrandeˇci´c and Kr¨otzsch, 2014). Many tasks including question answering and recommendation systems have benefited from KBs (Wang et al., 2017) as external knowledge sources to improve the results. Though KBs have achieved great success in supporting and improving various text mining tasks, they are still incomprehensible to humans due to the over-rigid structured format. Reading a bunch of triples always annoys people since the form is not easily understandable especially to people who have never heard about KBs. In order to address this problem, recently some researchers have proposed the KB-to-text generation task (Lebret et al., 2016; Gardent et al., 2017a; Gardent et al., 2017b) to bridge the gap between KBs and natural language. This KB-to-text generation problem aims at directly converting a group of KBs triples into human-readable sentences. For example, given a triple group ( ⟨Bill Gates, BirthPlace, Seattle ⟩, ⟨Bill Gates, FounderOf, Microsoft ⟩), the goal is to generate a comprehensible sentence such as “Bill Gates, the founder of Microsoft, was born in Seattle.” Some works employ the techniques in the text generation area (Gatt and Krahmer, 2018) to tackle the KB-to-text problem. Though these models have achieved some success, there are still quite many limi- tations. One major drawback of existing models is that most of them suffer from the off-topic problem. Consider the example given in Figure 1, the topic of the target sentence is expected to change from “per- son” to “company” …

Content truncated to 500 words