Hybrid named entity recognition for question-answering system

The main purpose of the intelligent question answering system based on the knowledge graph is to accurately match the natural language question and the triple information in the knowledge graph. Among them, the entity recognition part is one of the key points. The wrong entity recognition result will cause the error to be done propagated, resulting in the ultimate failure to get the correct answer. In recent years, the lexical enhancement structure of word nodes combined with word nodes has been proved to be an effective method for Chinese named entity recognition. In order to solve the above problems, this paper proposes a vocabulary-enhanced entity recognition algorithm (KGFLAT) based on FLAT for intelligent question answering system. This method uses a new dictionary that combines the entity information of the knowledge graph, and only uses layer normalization for the removal of residual connection for the shallower network model. The system uses data provided by the NLPCC 2018 Task7 KBQA task for evaluation. The experimental results show that this method can effectively solve the entity recognition task in the intelligent question answering system and achieve the improvement of the FLAT model, and the average F1 value is 94.72

Download Full-text

A literature review of question answering system using Named Entity Recognition

2016 3rd International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE) ◽

10.1109/icitacee.2016.7892454 ◽

2016 ◽

Cited By ~ 1

Author(s):

Rini Wongso ◽

Meiliana ◽

Derwin Suhartono

Keyword(s):

Literature Review ◽

Question Answering ◽

Named Entity Recognition ◽

Entity Recognition ◽

Question Answering System ◽

Named Entity

Download Full-text

Eve: An Automated Question Answering System for Events Information

ComTech Computer Mathematics and Engineering Applications ◽

10.21512/comtech.v8i1.3781 ◽

2017 ◽

Vol 8 (1) ◽

pp. 15

Author(s):

Ivan Christanno ◽

Priscilla Priscilla ◽

Jody Johansyah Maulana ◽

Derwin Suhartono ◽

Rini Wongso

Keyword(s):

Question Answering ◽

Named Entity Recognition ◽

Entity Recognition ◽

Closed Domain ◽

Word Similarity ◽

Question Answering System ◽

Named Entity ◽

Document Indexing ◽

Matching Technique ◽

Processing Information

The objective of this research was to create a closed-domain of automated question answering system specifically for events called Eve. Automated Question Answering System (QAS) is a system that accepts question input in the form of natural language. The question will be processed through modules to finally return the most appropriate answer to the corresponding question instead of returning a full document as an output. Thescope of the events was those which were organized by Students Association of Computer Science (HIMTI) in Bina Nusantara University. It consisted of 3 main modules namely query processing, information retrieval, and information extraction. Meanwhile, the approaches used in this system included question classification, document indexing, named entity recognition and others. For the results, the system can answer 63 questions for word matching technique, and 32 questions for word similarity technique out of 94 questions correctly.

Download Full-text