Intent Classification by the Use of Automatically Generated Knowledge Graphs
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 automa...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/5/288 |
| _version_ | 1827741144539201536 |
|---|---|
| author | Mihael Arcan Sampritha Manjunath Cécile Robin Ghanshyam Verma Devishree Pillai Simon Sarkar Sourav Dutta Haytham Assem John P. McCrae Paul Buitelaar |
| author_facet | Mihael Arcan Sampritha Manjunath Cécile Robin Ghanshyam Verma Devishree Pillai Simon Sarkar Sourav Dutta Haytham Assem John P. McCrae Paul Buitelaar |
| author_sort | Mihael Arcan |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T03:38:29Z |
| format | Article |
| id | doaj.art-5f2817ceddc74bdd8cc6f084aa0a9c0d |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T03:38:29Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-5f2817ceddc74bdd8cc6f084aa0a9c0d2023-11-18T01:48:08ZengMDPI AGInformation2078-24892023-05-0114528810.3390/info14050288Intent Classification by the Use of Automatically Generated Knowledge GraphsMihael Arcan0Sampritha Manjunath1Cécile Robin2Ghanshyam Verma3Devishree Pillai4Simon Sarkar5Sourav Dutta6Haytham Assem7John P. McCrae8Paul Buitelaar9Insight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandInsight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandInsight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandInsight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandInsight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandInsight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandHuawei Research, D02 R156 Dublin, IrelandAmazon Alexa AI, Cambridge CB1 2GA, UKInsight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandInsight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway, H91 AEX4 Galway, IrelandIntent 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.https://www.mdpi.com/2078-2489/14/5/288intent classificationterm extractionnamed entity extractionrelation extractionknowledge graph generation |
| spellingShingle | Mihael Arcan Sampritha Manjunath Cécile Robin Ghanshyam Verma Devishree Pillai Simon Sarkar Sourav Dutta Haytham Assem John P. McCrae Paul Buitelaar Intent Classification by the Use of Automatically Generated Knowledge Graphs Information intent classification term extraction named entity extraction relation extraction knowledge graph generation |
| title | Intent Classification by the Use of Automatically Generated Knowledge Graphs |
| title_full | Intent Classification by the Use of Automatically Generated Knowledge Graphs |
| title_fullStr | Intent Classification by the Use of Automatically Generated Knowledge Graphs |
| title_full_unstemmed | Intent Classification by the Use of Automatically Generated Knowledge Graphs |
| title_short | Intent Classification by the Use of Automatically Generated Knowledge Graphs |
| title_sort | intent classification by the use of automatically generated knowledge graphs |
| topic | intent classification term extraction named entity extraction relation extraction knowledge graph generation |
| url | https://www.mdpi.com/2078-2489/14/5/288 |
| work_keys_str_mv | AT mihaelarcan intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT samprithamanjunath intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT cecilerobin intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT ghanshyamverma intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT devishreepillai intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT simonsarkar intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT souravdutta intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT haythamassem intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT johnpmccrae intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs AT paulbuitelaar intentclassificationbytheuseofautomaticallygeneratedknowledgegraphs |