Systematic Knowledge Acquisition for Question Analysis

Proceedings of Recent Advances in Natural Language Processing, pages 406–412, Hissar, Bulgaria, 12-14 September 2011. Systematic Knowledge Acquisition for Question Analysis Dat Quoc Nguyen†,♯ and Dai Quoc Nguyen†,♯ and Son Bao Pham†,‡ † Faculty of Information Technology University of Engineering and Technology Vietnam National University, Hanoi {datnq, dainq, sonpb}@vnu.edu.vn ‡ Information Technology Institute Vietnam National University, Hanoi Abstract For the task of turning a natural language ques- tion into an explicit intermediate representa- tion of the complexity in question answering systems, all published works so far use rule- based approach to the best of our knowledge. We believe it is because of the complexity of the representation and the variety of question types and also there are no publicly available corpus of a decent size. In these rule-based ap- proaches, the process of creating rules is not discussed. It is clear that manually creating the rules in an ad-hoc manner is very expen- sive and error-prone. In this paper, we focus on the process of creating those rules manu- ally, in a way that consistency between rules is maintained and the effort to create a new rule is independent of the size of the current rule set. Experimental results are promising where our system achieves better performance and re- quires much less time and cognitive load com- pared to previous work. 1 Introduction The goal of question answering systems is to give an- swers to the user’s questions instead of ranked lists of related documents as used by most current search en- gines (Hirschman and Gaizauskas, 2001). Natural lan- guage question analysis component is the first compo- nent in any question answering systems. This compo- nent creates an intermediate representation of the input question, which is expressed in natural language, to be utilized in the rest of the system. In this paper, we introduce a language independent approach to systematically build a knowledge base for analyzing natural language questions. Natural language questions will be transformed into intermediate repre- sentation elements which include construction type of question, class of question, keywords in question and semantic constraints between them. Some question answering systems such as Aqualog (Lopez et al., 2007) and Vietnamese question answer- ing system (VnQAS) (Nguyen et al., 2009) manually ♯Both authors contributed equally to this work. defined a list of sequence pattern structures to analyze questions. As rules are created in an ad-hoc manner, these systems share a common difficulty in managing interaction between rules and keeping consistency. In our approach, we present an approach utilizing Ripple Down Rules (Compton and Jansen, 1990) (Richards, 2009) knowledge acquisition methodology to acquire rules in a systematic manner which avoids unintended interaction between rules. In section 2, we provide some related works and de- scribe our overall system architecture in section 3. We present our knowledge acquisition approach for ques- tion analysis in section 4. We describe our experiments in section 5. Discussion and conclusion will be pre- sented in section 6. 2 Related works 2.1 Question analysis in question answering systems …

Content truncated to 500 words