Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases

Proceedings of the 28th International Conference on Computational Linguistics, pages 2776–2786 Barcelona, Spain (Online), December 8-13, 2020 2776 Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases Sheng Bi1 and Xiya Cheng1 and Yuan-Fang Li2 and Yongzhen Wang3 and Guilin Qi1∗ 1School of Computer Science and Engineering, Southeast University, China 2Monash University, Melbourne, Australia 3Indiana University Bloomington, Bloomington, IN, USA {bisheng, chengxiya}@seu.edu.cn, yuanfang.li@monash.edu, wang11@iu.edu, gqi@seu.edu.cn Abstract Question generation over knowledge bases (KBQG) aims at generating natural-language ques- tions about a subgraph, i.e. a set of triples. Two main challenges still face the current crop of encoder-decoder-based methods, especially on small subgraphs: (1) low diversity and poor flu- ency due to the limited information contained in the subgraphs, and (2) semantic drift due to the decoder’s oblivion of the semantics of the answer entity. We propose an innovative knowledge- enriched, type-constrained and grammar-guided KBQG model, named KTG, to addresses the above challenges. In our model, the encoder is equipped with auxiliary information from the KB, and the decoder is constrained with word types during QG. Specifically, entity domain and description, as well as relation hierarchy information are considered to construct question contexts, while a conditional copy mechanism is incorporated to modulate question semantics according to current word types. Besides, a novel reward function featuring grammatical similar- ity is designed to improve both generative richness and syntactic correctness via reinforcement learning. Extensive experiments show that our proposed model outperforms existing methods by a significant margin on two widely-used benchmark datasets SimpleQuestion and PathQuestion. 1 Introduction Question Generation over Knowledge Bases (KBQG) aims to generate natural-language questions given a subgraph in the KB, i.e. a set of connected triples of the form <subject, predicate, object>. KBQG has a wide range of applications and is increasingly attracting attention from both academia and industry. For example, KBQG can improve factoid-based question answering (QA) systems by either dual training of QA and QG or by data augmentation for training corpora. As another example, KBQG can play a critical role in developing a chat-bot to ask KB-based questions under conversational settings. Table 1 illustrates a real scenario of KBQG, in which three questions are generated from two connected triples, along with the answer entity Ohio. Among the three questions, Q3 “Where was the high school of LeBron James, the American basketball player, located in?” is not only correct in grammars and semantics but also more diverse than Q1 because it contains the description information of LeBron James. Meanwhile, Q2 suffers a semantic drift problem due to a mismatch between the wrong interrogative “when” and Ohio whose entity type is location. Input <LeBron James, educated at, St. Vincent-St. Mary High School><St. Vincent-St. Mary High School, located in, Ohio> Output Diverse Question Correct Question Question Q1 ✗ ✓ Where was LeBron James’s high school located in? Q2 ✓ ✗ When was the high school of LeBron James, the American basketball player, located in? Q3 ✓ ✓ Where was the high school of LeBron James, the American basketball player, located …

Content truncated to 500 words