A Seq2seq-Based Approach to Question Answering over Knowledge Bases

Semantic parsing, as an essential approach to question answering over knowledge bases KBQA), transforms a question into query graphs for further generating logical queries. Existing semantic parsing approaches in KBQA mainly focus on relations (called local semantics) with paying less attention to the relationship among relations (called global semantics). In this paper, we present a seq2seq-based semantic parsing approach to improving performance of KBQA by converting the identification problem of question types to the problem of machine translation. Firstly, we introduce a BiLSTM-based named entity recognition (NER) method to extract all classes of entities occurring in questions. Secondly, we present an attention-based seq2seq model to learn one type of a question by applying seq2seq model in extracting relationships among classes. Finally, we generate templates to adopt more question types for matching more complex questions. The experimental results on a real knowledge base Chinese film show that our approach outperforms the existing template matching model.

[1]  Christian Biemann,et al.  Book Reviews: Ontology-Based Interpretation of Natural Language by Philipp Cimiano, Christina Unger and John McCrae , 2014, CL.

[2]  Seung-won Hwang,et al.  KBQA: Learning Question Answering over QA Corpora and Knowledge Bases , 2019, Proc. VLDB Endow..

[3]  Philipp Cimiano,et al.  Ontology-Based Interpretation of Natural Language , 2014, Ontology-Based Interpretation of Natural Language.

[4]  Ming-Wei Chang,et al.  Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base , 2015, ACL.

[5]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[6]  Gerhard Weikum,et al.  WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .

[7]  Bowen Zhou,et al.  Improved Neural Network-based Multi-label Classification with Better Initialization Leveraging Label Co-occurrence , 2016, NAACL.

[8]  Yue Wang,et al.  The APVA-TURBO Approach To Question Answering in Knowledge Base , 2018, COLING.

[9]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[10]  Feng Zhu,et al.  A novel CNN-based method for Question Classification in Intelligent Question Answering , 2018, ACAI.

[11]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[12]  Jose-Norberto Mazón,et al.  Model-driven adaptation of question answering systems for ambient intelligence by integrating restricted-domain knowledge , 2011, ICCS.

[13]  Diego Molla Aliod,et al.  Question Answering in Restricted Domains: An Overview , 2007, CL.

[14]  Johannes Fürnkranz,et al.  Large-Scale Multi-label Text Classification - Revisiting Neural Networks , 2013, ECML/PKDD.

[15]  Tiejun Zhao,et al.  Knowledge-Based Question Answering as Machine Translation , 2014, ACL.

[16]  Wei Xu,et al.  Bidirectional LSTM-CRF Models for Sequence Tagging , 2015, ArXiv.

[17]  A. Nugaliyadde,et al.  Advances in Natural Language Question Answering: A Review , 2019, ArXiv.

[18]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[19]  Elizabeth D. Liddy,et al.  Evaluation of Restricted Domain Question-Answering Systems , 2004, ACL 2004.

[20]  Jeff Z. Pan,et al.  Answer Type Identification for Question Answering - Supervised Learning of Dependency Graph Patterns from Natural Language Questions , 2015, JIST.

[21]  Xuchen Yao,et al.  Information Extraction over Structured Data: Question Answering with Freebase , 2014, ACL.

[22]  Markus Krötzsch,et al.  Wikidata , 2014, Commun. ACM.

[23]  Aditi Sharan,et al.  A framework for restricted domain Question Answering System , 2014, 2014 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT).