Open Information Extraction from Texts: Part III. Question Answering over an Automatically Constructed Knowledge Base
Lists
Only you see this
Abstract
In this paper, we propose a prototype question-answering system that works on top of an automatically generated knowledge base. The knowledge base is constructed using methods of open information extraction as well as unsupervised learning methods. In particular, various deep clustering methods are investigated and applied. Using open information extraction methods, triplets of the form {subject, predicate, object} are extracted, which are then clustered into semantic relations. The clustered triplets are collected into a graph database, which is a source of information to generate an answer. The developed prototype demonstrates the applicability of the results of the approach based on the methods of open information extraction and unsupervised machine learning to solving applied problems.
BibTeX
@inproceedings{chistova2022open,
author = {Elena Chistova and Daniil Larionov and E. A. Latypova and Artem Shelmanov and Ivan Smirnov},
title = {{Open Information Extraction from Texts: Part III. Question Answering over an Automatically Constructed Knowledge Base}},
booktitle = {Scientific},
year = {2022},
doi = {10.3103/s014768822206003x},
}Loading related content...