Intent Detection
Intent detection focuses on automatically identifying the user's goal or purpose from their input, whether text or speech, a crucial task for various applications like chatbots and personalized systems. Current research emphasizes improving accuracy and efficiency, particularly in handling out-of-domain queries and multiple simultaneous intents, often leveraging large language models (LLMs) and transformer-based architectures alongside traditional machine learning methods. This field is significant because accurate intent detection underpins the development of more robust and user-friendly human-computer interaction systems across diverse domains, from e-commerce to healthcare.
Papers
Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Mujeen Sung, James Gung, Elman Mansimov, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Yi Zhang, Vittorio Castelli
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade
Zefan Cai, Xin Zheng, Tianyu Liu, Xu Wang, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Baobao Chang, Yunbo Cao