A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910677851963392 |
|---|---|
| author | Mullick, Ankan Bose, Sombit Nandy, Abhilash Chaitanya, Gajula Sai Goyal, Pawan |
| author_facet | Mullick, Ankan Bose, Sombit Nandy, Abhilash Chaitanya, Gajula Sai Goyal, Pawan |
| contents | In task-oriented dialogue systems, intent detection is crucial for interpreting user queries and providing appropriate responses. Existing research primarily addresses simple queries with a single intent, lacking effective systems for handling complex queries with multiple intents and extracting different intent spans. Additionally, there is a notable absence of multilingual, multi-intent datasets. This study addresses three critical tasks: extracting multiple intent spans from queries, detecting multiple intents, and developing a multi-lingual multi-label intent dataset. We introduce a novel multi-label multi-class intent detection dataset (MLMCID-dataset) curated from existing benchmark datasets. We also propose a pointer network-based architecture (MLMCID) to extract intent spans and detect multiple intents with coarse and fine-grained labels in the form of sextuplets. Comprehensive analysis demonstrates the superiority of our pointer network-based system over baseline approaches in terms of accuracy and F1-score across various datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22476 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents Mullick, Ankan Bose, Sombit Nandy, Abhilash Chaitanya, Gajula Sai Goyal, Pawan Computation and Language Information Retrieval In task-oriented dialogue systems, intent detection is crucial for interpreting user queries and providing appropriate responses. Existing research primarily addresses simple queries with a single intent, lacking effective systems for handling complex queries with multiple intents and extracting different intent spans. Additionally, there is a notable absence of multilingual, multi-intent datasets. This study addresses three critical tasks: extracting multiple intent spans from queries, detecting multiple intents, and developing a multi-lingual multi-label intent dataset. We introduce a novel multi-label multi-class intent detection dataset (MLMCID-dataset) curated from existing benchmark datasets. We also propose a pointer network-based architecture (MLMCID) to extract intent spans and detect multiple intents with coarse and fine-grained labels in the form of sextuplets. Comprehensive analysis demonstrates the superiority of our pointer network-based system over baseline approaches in terms of accuracy and F1-score across various datasets. |
| title | A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2410.22476 |