paper-with-me

홈 › Papers

一种结合话语伪标签注意力的人机对话意图分类方法(A Human-machine Dialogue Intent Classification Method using Utterance Pseudo Label Attention)

2020-10-01 · CCL 2020 10 · Jiande Ding, Peijie Huang, Jiabao Xu, Youming Peng

在人机对话中,系统需要通过意图分类判断用户意图,再触发相应的业务类型。由于多轮人机对话具有口语化、长文本和特征稀疏等特点,现有的文本分类方法在人机对话意图分类上还存在较大困难。本文在层次注意力网络(hierarchical attention networks, HAN)基础上,提出了一种结合话语伪标签注意力的层次注意力网络模型PLA-HAN (HAN with utterance pseudo label attention)。PLA-HAN通过优选伪标签集、构建单句话语意图识别模型以及设计话语伪标签注意力机制,识别单句话语意图伪标签,并计算话语伪标签注意力。进而将单句话语伪标签注意力嵌入到HAN的层级结构中,与HAN中的句子级别注意力相融合。融合了单句话语意图信息的句子级注意力使模型整体性能得到进一步的提升。我们在中国中文信息学会主办的“客服领域用户意图分类评测比赛”的评测语料上进行实验,实验结果证明PLA-HAN模型取得了优于HAN等对比方法的意图分类性能。

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

intent-classificationIntent ClassificationPseudo Label

Similar Papers 제목 키워드 기반

Contextual Dialogue Act Classification for Open-Domain Conversational Agents

2020-05-28 · Ali Ahmadvand, Jason Ingyu Choi, Eugene Agichtein

Classifying the general intent of the user utterance in a conversation, also known as Dialogue Act (DA), e.g., open-ended question, statement of opinion, or request for an opinion, is a key step in Natural Language Under…

ClassificationDialogue Act ClassificationGeneral ClassificationNatural Language Understanding+1

LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue

2025-12-24 · Jinqiang Wang, Huansheng Ning, Jianguo Ding, Tao Zhu 외 arxiv

Proactively predicting a users next utterance in human-machine dialogue can streamline interaction and improve user experience. Existing commercial API-based solutions are subject to privacy concerns while deploying gene…

Improved intent classification based on context information using a windows-based approach

2024-11-09 · Jeanfranco D. Farfan-Escobedo, Julio C. Dos Reis

Conversational systems have a Natural Language Understanding (NLU) module. In this module, there is a task known as an intent classification that aims at identifying what a user is attempting to achieve from an utterance…

Classificationintent-classificationIntent ClassificationNatural Language Understanding

Utterance Intent Classification of a Spoken Dialogue System with Efficiently Untied Recursive Autoencoders

2017-08-01 · WS 2017 8 · Tsuneo Kato, Atsushi Nagai, Naoki Noda, Ryosuke Sumitomo 외

Recursive autoencoders (RAEs) for compositionality of a vector space model were applied to utterance intent classification of a smartphone-based Japanese-language spoken dialogue system. Though the RAEs express a nonline…

Automatic Speech Recognition (ASR)ClassificationGeneral Classificationintent-classification+4

InferEM: Inferring the Speaker's Intention for Empathetic Dialogue Generation

2022-12-13 · Guoqing Lv, Jiang Li, XiaoPing Wang, Zhigang Zeng

Current approaches to empathetic response generation typically encode the entire dialogue history directly and put the output into a decoder to generate friendly feedback. These methods focus on modelling contextual info…

DecoderDialogue GenerationEmpathetic Response GenerationMulti-Task Learning+1