Affiliation:
1. The Chinese University of Hong Kong, Hong Kong
2. Alibaba Group, China
3. Alibaba Group, Bellevue, WA, USA
4. SIAT, Chinese Academy of Sciences, Shenzhen, China
5. Sun Yat-Sen University, Guangzhou, China
Abstract
Answer selection, which is involved in many natural language processing applications, such as dialog systems and question answering (QA), is an important yet challenging task in practice, since conventional methods typically suffer from the issues of ignoring diverse real-world background knowledge. In this article, we extensively investigate approaches to enhancing the answer selection model with external knowledge from knowledge graph (KG). First, we present a context-knowledge interaction learning framework, Knowledge-aware Neural Network, which learns the QA sentence representations by considering a tight interaction with the external knowledge from KG and the textual information. Then, we develop two kinds of knowledge-aware attention mechanism to summarize both the context-based and knowledge-based interactions between questions and answers. To handle the diversity and complexity of KG information, we further propose a Contextualized Knowledge-aware Attentive Neural Network, which improves the knowledge representation learning with structure information via a customized Graph Convolutional Network and comprehensively learns context-based and knowledge-based sentence representation via the multi-view knowledge-aware attention mechanism. We evaluate our method on four widely used benchmark QA datasets, including WikiQA, TREC QA, InsuranceQA, and Yahoo QA. Results verify the benefits of incorporating external knowledge from KG and show the robust superiority and extensive applicability of our method.
Funder
Research Grant Council of the Hong Kong Special Administrative Region, China
Shenzhen General Research Project
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Science Applications,General Business, Management and Accounting,Information Systems
Reference69 articles.
1. Freebase
2. Translating embeddings for modeling multi-relational data. In Proceedings of the 27th Annual Conference on Neural Information Processing Systems;Bordes Antoine;Advances in Neural Information Processing Systems,2013
3. Re-ranking Answer Selection with Similarity Aggregation
4. Enhancing Recurrent Neural Networks with Positional Attention for Question Answering
Cited by
16 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献