Intent Classification by the Use of Automatically Generated Knowledge Graphs

Author:

Arcan Mihael1ORCID,Manjunath Sampritha1ORCID,Robin Cécile1ORCID,Verma Ghanshyam1ORCID,Pillai Devishree1ORCID,Sarkar Simon1,Dutta Sourav2ORCID,Assem Haytham3,McCrae John P.1ORCID,Buitelaar Paul1ORCID

Affiliation:

1. Insight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, Ireland

2. Huawei Research, D02 R156 Dublin, Ireland

3. Amazon Alexa AI, Cambridge CB1 2GA, UK

Abstract

Intent classification is an essential task for goal-oriented dialogue systems for automatically identifying customers’ goals. Although intent classification performs well in general settings, domain-specific user goals can still present a challenge for this task. To address this challenge, we automatically generate knowledge graphs for targeted data sets to capture domain-specific knowledge and leverage embeddings trained on these knowledge graphs for the intent classification task. As existing knowledge graphs might not be suitable for a targeted domain of interest, our automatic generation of knowledge graphs can extract the semantic information of any domain, which can be incorporated within the classification process. We compare our results with state-of-the-art pre-trained sentence embeddings and our evaluation of three data sets shows improvement in the intent classification task in terms of precision.

Funder

Science Foundation Ireland

Publisher

MDPI AG

Subject

Information Systems

Reference32 articles.

1. The influence of goal attainment and switching costs on customers’ staying intentions;Temerak;J. Retail. Consum. Serv.,2019

2. Abujabal, A., Roy, R.S., Yahya, M., and Weikum, G. (2018). ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters. arXiv.

3. Fader, A., Zettlemoyer, L., and Etzioni, O. (2013, January 4–9). Paraphrase-Driven Learning for Open Question Answering. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria.

4. DBpedia—A Large-scale, Multilingual Knowledge Base Extracted from Wikipedia;Lehmann;Semant. Web J.,2015

5. Cavalin, P., Alves Ribeiro, V.H., Appel, A., and Pinhanez, C. (2020, January 16–20). Improving Out-of-Scope Detection in Intent Classification by Using Embeddings of the Word Graph Space of the Classes. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3