English

A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents

Computation and Language 2024-10-31 v1 Information Retrieval

Abstract

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.

Keywords

Cite

@article{arxiv.2410.22476,
  title  = {A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents},
  author = {Ankan Mullick and Sombit Bose and Abhilash Nandy and Gajula Sai Chaitanya and Pawan Goyal},
  journal= {arXiv preprint arXiv:2410.22476},
  year   = {2024}
}

Comments

Accepted at EMNLP 2024 Findings (Long Paper)

R2 v1 2026-06-28T19:40:19.619Z