Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding
In Spoken Language Understanding (SLU), the ability to detect out-of-domain (OOD) input dialog plays a very important role (e.g., voice assistance and chatbot systems). However, most of the existing OOD detection methods rely heavily on manually labeled OOD data. Manual labeling of the OOD data for...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9641813/ |
| _version_ | 1828179381319630848 |
|---|---|
| author | Niraj Kumar Bhiman Kumar Baghel |
| author_facet | Niraj Kumar Bhiman Kumar Baghel |
| author_sort | Niraj Kumar |
| collection | DOAJ |
| description | In Spoken Language Understanding (SLU), the ability to detect out-of-domain (OOD) input dialog plays a very important role (e.g., voice assistance and chatbot systems). However, most of the existing OOD detection methods rely heavily on manually labeled OOD data. Manual labeling of the OOD data for a dynamically changing and evolving area is time-consuming and not immediately possible. It limits the feasibility of these models in practical applications. So, to solve this problem, we are considering the scenario of having no OOD labeled data (i.e., zero-shot learning). To achieve this goal, we have used the intent focused semantic parsing, extracted with the help of Transformer-based techniques [e.g., BERT (Devlin <italic>et al.</italic>, 2018)]. The two main components of the intent-focused semantic parsing are - (a) the sentence-level intents and (b) token-level intent classes, which show the relation of slot tokens with intent classes. Finally, we combine both information and use a One Class Neural Network (OC-NN) based zero-shot classifier. Our devised system has shown better results compared to the state-of-the-art on four publicly available datasets. |
| first_indexed | 2024-04-12T05:28:33Z |
| format | Article |
| id | doaj.art-e60f09187084459f945eb6d45ad6a7d9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T05:28:33Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e60f09187084459f945eb6d45ad6a7d92022-12-22T03:46:11ZengIEEEIEEE Access2169-35362021-01-01916578616579410.1109/ACCESS.2021.31336579641813Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language UnderstandingNiraj Kumar0https://orcid.org/0000-0002-5498-1997Bhiman Kumar Baghel1https://orcid.org/0000-0002-6439-5844Samsung Research Institute, Bengaluru, IndiaSamsung Research Institute, Bengaluru, IndiaIn Spoken Language Understanding (SLU), the ability to detect out-of-domain (OOD) input dialog plays a very important role (e.g., voice assistance and chatbot systems). However, most of the existing OOD detection methods rely heavily on manually labeled OOD data. Manual labeling of the OOD data for a dynamically changing and evolving area is time-consuming and not immediately possible. It limits the feasibility of these models in practical applications. So, to solve this problem, we are considering the scenario of having no OOD labeled data (i.e., zero-shot learning). To achieve this goal, we have used the intent focused semantic parsing, extracted with the help of Transformer-based techniques [e.g., BERT (Devlin <italic>et al.</italic>, 2018)]. The two main components of the intent-focused semantic parsing are - (a) the sentence-level intents and (b) token-level intent classes, which show the relation of slot tokens with intent classes. Finally, we combine both information and use a One Class Neural Network (OC-NN) based zero-shot classifier. Our devised system has shown better results compared to the state-of-the-art on four publicly available datasets.https://ieeexplore.ieee.org/document/9641813/Spoken language understandingout-of-domain (OOD) detectionzero-shot learningintent focused semantic parsing |
| spellingShingle | Niraj Kumar Bhiman Kumar Baghel Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding IEEE Access Spoken language understanding out-of-domain (OOD) detection zero-shot learning intent focused semantic parsing |
| title | Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding |
| title_full | Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding |
| title_fullStr | Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding |
| title_full_unstemmed | Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding |
| title_short | Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding |
| title_sort | intent focused semantic parsing and zero shot learning for out of domain detection in spoken language understanding |
| topic | Spoken language understanding out-of-domain (OOD) detection zero-shot learning intent focused semantic parsing |
| url | https://ieeexplore.ieee.org/document/9641813/ |
| work_keys_str_mv | AT nirajkumar intentfocusedsemanticparsingandzeroshotlearningforoutofdomaindetectioninspokenlanguageunderstanding AT bhimankumarbaghel intentfocusedsemanticparsingandzeroshotlearningforoutofdomaindetectioninspokenlanguageunderstanding |