@inproceedings{5f9a4cac7b2f4067862f404502a1804f,
title = "Automatic ontology learning from domain-specific short unstructured text data",
abstract = "Ontology learning is a critical task in industry, which deals with identifying and extracting concepts reported in text such that these concepts can be used in different tasks, e.g. information retrieval. The problem of ontology learning is non-trivial due to several reasons with a limited amount of prior research work that automatically learns a domain specific ontology from data. In our work, we propose a two-stage classification system to automatically learn an ontology from unstructured text. In our model, the first-stage classifier classifies candidate concepts into relevant and irrelevant concepts and then the second-stage classifier assigns specific classes to the relevant concepts. The proposed system is deployed as a prototype in General Motors and its performance is validated by using complaint and repair verbatim data collected from different data sources. On average, our system shows the F1-score of 0.75, even when data distributions are vastly different.",
keywords = "Classification, Clustering, Information systems, Ontology learning",
author = "Yiming Xu and Dnyanesh Rajpathak and Ian Gibbs and Diego Klabjan",
note = "Publisher Copyright: Copyright {\textcopyright} 2020 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.; 12th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2020 - Part of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2020 ; Conference date: 02-11-2020 Through 04-11-2020",
year = "2020",
doi = "10.5220/0009980100290039",
language = "English (US)",
series = "IC3K 2020 - Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management",
publisher = "SciTePress",
pages = "29--39",
editor = "Ana Salgado and Jorge Bernardino and Joaquim Filipe",
booktitle = "KMIS",
}