Abstract
Comparative questions in Chinese, as a special and complex form of question answering (QA), have their own unique sentence structure, existing methods cannot solve them well. Inspired by cognitive studies on how humans solve complex problems, we propose a hybrid framework which combines Logic Programming and attention based Bi-LSTM. This framework is decomposed into three consecutive components: 1) identify comparative questions, 2) extract comparative elements from the identified comparative questions, and 3) answer factoid questions containing the extracted comparative elements. Specifically, for the former two components, Logic Programming is adopted to filter out non-comparative questions and extract comparative elements. For the latter one, a bidirectional long and short term memory (Bi-LSTM) model with attention mechanism is utilized. Experimental results on Chinese geographical question datasets show that our proposed hybrid framework achieves outstanding performance for practical use.
Highlights
Question answering [1] is a difficult NLP task due to the diversity and complexity of questions
Since Logic Programming can provide detail-giving, natural-language explanations for its answers, we propose to employ answer set programming (ASP) to extract comparative elements by using heuristics and dependency grammar to represent the relations among comparative elements
The major contributions of this paper could be summarized as follows: (1) Inspired by the idea of shaping, we propose a hybrid framework for problem solving of comparative questions by combining Logic Programming and attention based Bi-long short term memory (LSTM), due to the complexity and difficulty of comparative questions
Summary
Question answering [1] is a difficult NLP task due to the diversity and complexity of questions. For component 2, some existing studies [11], [12] have shown that the rule-based approach is more suitable for extracting comparative elements due to the structural uniqueness of comparative sentences. Since Logic Programming can provide detail-giving, natural-language explanations for its answers, we propose to employ ASP to extract comparative elements by using heuristics (such as word position) and dependency grammar to represent the relations among comparative elements This content of component 1 and component 2 was studied in detail in [13]. (1) Inspired by the idea of shaping, we propose a hybrid framework for problem solving of comparative questions by combining Logic Programming and attention based Bi-LSTM, due to the complexity and difficulty of comparative questions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
