A key challenge of dialog systems research is to effectively and efficiently adapt to new domains. A scalable paradigm for adaptation necessitates the development of generalizable models that perform well in few-shot settings. In this paper, we focus on the intent classification problem which aims to identify user intents given utterances addressed to the dialog system. We propose two approaches for improving the generalizability of utterance classification models: (1) observers and (2) example-driven training. Prior work has shown that BERT-like models tend to attribute a significant amount of attention to the [CLS] token, which we hypothesize results in diluted representations. Observers are tokens that are not attended to, and are an alternative to the [CLS] token as a semantic representation of utterances. Example-driven training learns to classify utterances by comparing to examples, thereby using the underlying encoder as a sentence similarity model. These methods are complementary; improving the representation through observers allows the example-driven model to better measure sentence similarities. When combined, the proposed methods attain state-of-the-art results on three intent prediction datasets (\textsc{banking77}, \textsc{clinc150}, \textsc{hwu64}) in both the full data and few-shot (10 examples per intent) settings. Furthermore, we demonstrate that the proposed approach can transfer to new intents and across datasets without any additional training.
Exploring news intent and its application: A theory-driven approach
Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences(计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);University of Macau(澳门大学);Communication University of China(中国传媒大学)
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework
Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University(天津认知计算与应用重点实验室,智能计算学院,天津大学);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东人工智能与数字经济实验室(深圳));Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院);College of Computer Science and Software Engineering, Shenzhen University(计算机科学与软件工程学院,深圳大学);Huiyan Technology (Tianjin) Co., Ltd(慧研科技(天津)有限公司)
Thinking Like a Botanist: Challenging Multimodal Language Models with Intent-Driven Chain-of-Inquiry
Department of Robotics and Mechatronics Engineering, University of Dhaka(达卡大学机器人与机电工程系);Department of Computer Science and Engineering, University of Dhaka(达卡大学计算机科学与工程系);Department of Agronomy, Gazipur Agricultural University(加兹ipur农业大学作物学系);Department of Botany, University of Dhaka(达卡大学植物学系)
V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(上海交通大学自动化与智能感知学院);Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University(上海交通大学图像处理与模式识别研究所);SenseTime Research(商汤科技研究院);Institute of Medical Robotics, Shanghai Jiao Tong University(上海交通大学医学机器人研究所)
Large Language Models for Intent-Driven Session Recommendations
Center for Frontier AI Research, A*STAR(新加坡科技研究局前沿人工智能研究中心);Institute of High Performance Computing, A*STAR(新加坡科技研究局高性能计算研究所);Macquarie University(麦考瑞大学);Shanda Group AI Lab(盛大多媒体集团人工智能实验室);Yan Shan University(燕山大学);Nanyang Technological University(南洋理工大学)