Discovering Conversational Dependencies between Messages in Dialogs
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 that leverages conversational, lexical and semantic information. The approach is evaluated empirically on a set of customer service chat logs from a Chinese e-commerce website. It outperforms heuristic baselines.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
FunctionChat-Bench: Comprehensive Evaluation of Language Models' Generative Capabilities in Korean Tool-use Dialogs
This study investigates language models' generative capabilities in tool-use dialogs. We categorize the models' outputs in tool-use dialogs into four distinct types: Tool Call, Answer Completion, Slot Question, and Relev…
Relevance DetectionDependency Parsing for Spoken Dialog Systems
Dependency parsing of conversational input can play an important role in language understanding for dialog systems by identifying the relationships between entities extracted from user utterances. Additionally, effective…
ArticlesDependency ParsingDialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs
Real-world conversational agents must effectively handle long conversations that span multiple contexts. Such context can be interspersed with chitchat (dialog turns not directly related to the task at hand), and potenti…
Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity
Open-ended human learning and information-seeking are increasingly mediated by digital assistants. However, such systems often ignore the user's pre-existing knowledge. Assuming a correlation between engagement and user …
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness. To tackle thes…
Conversational RecommendationDiversityFew-Shot LearningLanguage Modeling+2