PhD Dissertation Proposal by LAN Yunshi | Using Knowledge Bases for Textual Entailment and Question Answering

A knowledge base (KB) is a well-structured database, which contains many of entities and their relations. With the fast development of large-scale knowledge bases such as Freebase, DBpedia and YAGO, knowledge bases have become an important resource, which can serve many applications, such as dialogue system, textual entailment, question answering and so on. These applications play significant roles in real-world industry. In this dissertation, we try to explore how we can use knowledge bases for textual entailment and question answering. Recognizing textual entailment (RTE) is a task to infer the entailment relations between sentences. We need to decide whether a hypothesis can be inferred from a premise based on the text of two sentences. Such entailment relations could be potentially useful in applications like information retrieval and commonsense reasoning. It’s necessary to develop automatic techniques to solve this problem. Another task is knowledge base question answering (KBQA). This task aims to automatically find answers to factoid questions from a knowledge base, where answers are usually entities in the KB. KBQA task has gained much attention in recent years and shown promising contribution to real-world problems. In this dissertation, we try to study the applications of knowledge bases in textual entailment and question answering: 1) We propose a general neural network based framework which can inject lexical entailment relations to RTE, and a novel model is developed to embed lexical entailment relations. The experiment results show that our method can benefit general textual entailment model. 2) We design a KBQA method based on an existing reading comprehension model. This model achieves competitive results on several popular KBQA datasets. In addition, we make full use of contextual relations of entities in the KB. Such enriched information helps our model to attain state-of-art. 3) We further investigate multi-hop KBQA task, i.e., question answering from KB where questions involve multiple hops of relations, and develop a novel model to solve such questions in an iterative and efficient way. The results demonstrate that our method consistently outperforms several strong baselines.

Yunshi LAN is a PhD candidate at School of Information Systems, Singapore Management University. She is advised by Associate Professor Jing Jiang and Associate Professor Feida Zhu. Her research interests are in applications of knowledge bases in Natural Language Processing like textual entailment, knowledge base question answering, etc..