118093 - Open-domain question answering framework using Wikipedia.pdf (621.6 kB)
Open-domain question answering framework using Wikipedia
conference contribution
posted on 2023-05-23, 12:12 authored by Saleem AmeenSaleem Ameen, Hyunsuk Chung, Han, SC, Byeong KangByeong KangThis paper explores the feasibility of implementing a model for an open domain, automated question and answering framework that leverages Wikipedia’s knowledgebase. While Wikipedia implicitly comprises answers to common questions, the disambiguation of natural language and the difficulty of developing an information retrieval process that produces answers with specificity present pertinent challenges. However, observational analysis suggests that it is possible to discount the syntactical and lexical structure of a sentence in contexts where questions contain a specific target entity (words that identify a person, location or organisation) and that correspondingly query a property related to it. To investigate this, we implemented an algorithmic process that extracted the target entity from the question using CRF based named entity recognition (NER) and utilised all remaining words as potential properties. Using DBPedia, an ontological database of Wikipedia’s knowledge, we searched for the closest matching property that would produce an answer by applying standardised string matching algorithms including the Levenshtein distance, similar text and Dice’s coefficient. Our experimental results illustrate that using Wikipedia as a knowledgebase produces high precision for questions that contain a singular unambiguous entity as the subject, but lowered accuracy for questions where the entity exists as part of the object.
History
Publication title
Lecture Notes in Computer Science 9992: Proceedings of the 29th Australasian Joint Conference on Artificial Intelligence (AI 2016): Advances in Artificial Intelligence)Editors
BH Kang & Q BaiPagination
623-635ISBN
978-3-319-50127-7Department/School
School of Information and Communication TechnologyPublisher
Springer International PublishingPlace of publication
SwitzerlandEvent title
29th Australasian Joint Conference on Artificial Intelligence (AI 2016): Advances in Artificial IntelligenceEvent Venue
Hobart, TasmaniaDate of Event (Start Date)
2016-12-05Date of Event (End Date)
2016-12-08Rights statement
Copyright 2016 Springer International Publishing AG. This is an author-created version of a paper originally published in, Kang B., Bai Q. (eds) AI 2016: Advances in Artificial Intelligence. AI 2016. Lecture Notes in Computer Science, vol 9992. Springer, Cham. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-50127-7_55Repository Status
- Open