paper-with-me

Papers

Discovering Customer-Service Dialog System with Semi-Supervised Learning and Coarse-to-Fine Intent Detection

2022-12-23 · Zhitong Yang, Xing Ma, Anqi Liu, Zheyu Zhang

Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation. Recently, good results have been obtained based on large pre-trained models. However, the labeled-data scarcity hinders the efficient development of TOD systems at scale. In this work, we constructed a weakly supervised dataset based on a teacher/student paradigm that leverages a large collection of unlabelled dialogues. Furthermore, we built a modular dialogue system and integrated coarse-to-fine grained classification for user intent detection. Experiments show that our method can reach the dialog goal with a higher success rate and generate more coherent responses.

📄 PDF Abstract BibTeX arXiv:2212.12363

Code (0)

등록된 구현이 없습니다.

Tasks

Intent Detection

Similar Papers 제목 키워드 기반

Discovering Conversational Dependencies between Messages in Dialogs

2016-12-08 · Wenchao Du, Pascal Poupart, Wei Xu

We investigate the task of inferring conversational dependencies between messages in one-on-one online chat, which has become one of the most popular forms of customer service. We propose a novel probabilistic classifier…

Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues

2024-12-12 · Mengze Hong, Wailing Ng, Chen Jason Zhang, Yuanfeng Song 외

Discovering customer intentions in dialogue conversations is crucial for automated service agents. However, existing intent clustering methods often fail to align with human perceptions due to a heavy reliance on embeddi…

ClusteringCoherence EvaluationIntent DiscoveryText Clustering

Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling

2020-12-14 · Yicheng Zou, Lujun Zhao, Yangyang Kang, Jun Lin 외

In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics. I…

"How May I Help You?": Modeling Twitter Customer Service Conversations Using Fine-Grained Dialogue Acts

2017-09-15 · Shereen Oraby, Pritam Gundecha, Jalal Mahmud, Mansurul Bhuiyan 외

Given the increasing popularity of customer service dialogue on Twitter, analysis of conversation data is essential to understand trends in customer and agent behavior for the purpose of automating customer service inter…

Semi-Supervised Clustering with Contrastive Learning for Discovering New Intents

2022-01-07 · Feng Wei, Zhenbo Chen, Zhenghong Hao, Fengxin Yang 외

Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considerin…

ClusteringContrastive LearningText Clustering