Semantic Search on Non-Factoid Questions for Domain-Specific Question Answering Systems

被引：0
作者：
Qiu Y. [1 ,2 ,3 ]
Cheng L. [1 ,2 ,3 ]
Alghazzawi D. [4 ]
机构：
[1] Xinjiang Technical Institute of Physics & Chemistry, Chinese Academy of Sciences, Urumqi
[2] University of Chinese Academy of Sciences, Beijing
[3] Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi
[4] Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah
来源：
Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis | 2019年 / 55卷 / 01期
关键词：
Domain knowledge base; Learning to rank; Non-factoid question; Question answering system; Semantic search;
D O I：
10.13209/j.0479-8023.2018.068
中图分类号：
学科分类号：
摘要：
A semantic-based retrieval method was proposed to extract answer sentences from tax regulations and cases. Firstly, a domain knowledge base was employed to generate semantic annotations for questions, regulations and cases. Secondly, a filtering system was developed for the removal of irrelevant cases from answer candidates. In addition, a semantic similarity measurement method was employed for answer extraction. Finally, a rank model was proposed for the optimization of the retrieved results. In order to validate the proposed method, a series of experiments were performed on real-life dataset. Experiment results show noticeable improvement in accuracy and performance compared to the baseline methods. © 2019 Peking University.
引用
收藏
页码：55 / 64
页数：9
相关论文
共 27 条
  • [1] Surdeanu M., Ciaramita M., Zaragoza H., Learning to rank answers to non-factoid questions from web collections, Computational Linguistics, 37, 2, pp. 351-383, (2011)
  • [2] Yang L., Ai Q., Spina D., Et al., Beyond factoid QA: effective methods for non-factoid answer sentence retrieval, European Conference on Information Retrieval, pp. 115-128, (2016)
  • [3] Othman N., Faiz R., Question answering passage retrieval and re-ranking using n-grams and SVM, Computación y Sistemas, 20, 3, pp. 483-494, (2016)
  • [4] Fukumoto J., Question answering system for non-factoid type questions and automatic evaluation based on BE method, The 7th NTCIR Workshop, pp. 441-447, (2007)
  • [5] Tran O.T., Ngo B.X., Le Nguyen M., Et al., Answering legal questions by mining reference information, JSAI International Symposium on Artificial Intelligence, pp. 214-229, (2013)
  • [6] Savenkov D., Ranking answers and web passages for non-factoid question answering: emory university at TREC LiveQA, The Twenty-Fourth Text REtrieval Conference (TREC 2015), pp. 1-8, (2015)
  • [7] Prolo C., Quaresma P., Rodrigues I., Et al., A question-answering system for portuguese, Knowledge and Reasoning for Answering Questions. Workshop Associated with IJCAI05, pp. 45-48, (2005)
  • [8] Monroy A., Calvo H., Gelbukh A., NLP for shallow question answering of legal documents using graphs, International Conference on Intelligent Text Processing and Computational Linguistics, pp. 498-508, (2009)
  • [9] Kim M.Y., Xu Y., Goebel R., Legal question answering using ranking svm and syntactic/semantic similarity, JSAI International Symposium on Artificial Intelligence, pp. 244-258, (2014)
  • [10] Qiu Y., Cheng L., Alghazzawi D., Towards a semi-automatic method for building Chinese tax domain ontology, 201713th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), pp. 2530-2539, (2017)
123