Leveraging Domain Context for Question Answering Over Knowledge Graph

Abstract

With the growing availability of different knowledge graphs in a variety of domains, question answering over knowledge graph (KG-QA) becomes a prevalent information retrieval approach. Current KG-QA methods usually resort to semantic parsing, search or neural matching models. However, they cannot well tackle increasingly long input questions and complex information needs. In this work, we propose a new KG-QA approach, leveraging the rich domain context in the knowledge graph. We incorporate the new approach with question and answer domain context descriptions. Specifically, for questions, we enrich them with users' subsequent input questions within a session and expand the input question representation. For the candidate answers, we equip them with surrounding context structures, i.e., meta-paths within the targeting knowledge graph. On top of these, we design a cross-attention mechanism to improve the question and answer matching performance. An experimental study on real datasets verifies these improvements. The new approach is especially beneficial for specific knowledge graphs with complex questions.

Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs

“…Tai et al (2015) introduced Tree-LSTM for computing tree embeddings bottom-up. It has then been applied for many tasks, including computer program translation , se-mantic tree structure learning (such as JSON or XML) (Woof and Chen, 2020) and supervised KG-QA tasks (Tong et al, 2019;Zafar et al, 2019;Athreya et al, 2020). In the latter context, Tree-LSTM is used to model the syntactic structure of the question.…”

“…Second, most of the semantic parsing models do not leverage much of the underlying KG structure to predict the LF, as in Dong and Lapata (2016); Guo et al (2018). Yet, this contextual graph information is rich (Tong et al, 2019), and graph-based models leveraging this information yield promising results for KG-QA tasks (Vakulenko et al, 2019;Christmann et al, 2019). However these alternative approaches to semantic parsing, that rely on node classification, have their inherent limitations, as they handle less naturally certain queries (see Appendix C.2) and their output is less interpretable.…”

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification

“…Relation classification (RC) is one of the most important techniques in natural language processing (NLP) and has various applications such as information retrieval (Ercan et al, 2019), question answering (Tong et al, 2019) and dialogue systems (Ma et al, 2019). Currently, conventional deep supervised (Zeng et al, 2014;Gormley et al, 2015) and distantly supervised (Mintz et al, 2009;Jiang et al, 2016;Ye and Ling, 2019a) RC models are widely used and achieve remarkable performance.…”

TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process

“…( 4) Content-introducing methods (Mou et al, 2016;Yao et al, 2017). ( 5) Knowledge-based methods (Zhou et al, 2018;Tong et al, 2019 account to facilitate conversation understanding. In the decoding process, these models always use a single decoder to generate the final response at a stroke in a left-to-right manner.…”