Information-Seeking Chat: Dialogue Management by Topic Structure
نویسنده
چکیده
In this paper we describe the dialogue sub-genre “information-seeking chat”, which is distinguished from other kinds of information-seeking dialogue (e.g. travel information) by its more exploratory and less (single) task-oriented nature. We present an approach to modelling this kind of dialogue, based on the notion of weighted topic structures — a single data structure that represents both the domain knowledge and the dialogue history, and we sketch an implementation of this approach in a typed dialogue system.
منابع مشابه
Annotating Topic Development in Information Seeking Queries
This paper contributes to the limited body of empirical research in the domain of discourse structure of information seeking queries. We describe the development of an annotation schema for coding topic development in information seeking queries and the initial observations from a pilot sample of query sessions. The main idea that we explore is the relationship between constant and variable dis...
متن کاملDialogue Management for Language-Based Information Seeking
While the dialogue management for information seeking on table-based structured databases has been actively researched, little has been done on the management of language-based questionanswering dialogues. This paper discusses how to incorporate some of the state-of-the-art techniques for information-seeking dialogue management into language-based question answering, proposing a basic framework...
متن کاملDistributed dialogue management in a blackboard architecture
This paper describes a distributed dialogue management scheme for speechbased information seeking dialogue. The dialogue management is distributed to several components, supported by a general blackboard-type architecture for speech systems. By breaking down the dialogue management, we can achieve more general solutions and support sophisticated decision making algorithms.
متن کاملClassifying Dialogue Acts in One-on-One Live Chats
We explore the task of automatically classifying dialogue acts in 1-on-1 online chat forums, an increasingly popular means of providing customer service. In particular, we investigate the effectiveness of various features and machine learners for this task. While a simple bag-of-words approach provides a solid baseline, we find that adding information from dialogue structure and inter-utterance...
متن کاملExtracting Keywords from Multi-party Live Chats
Live chats have become a popular form of communication, connecting people all over the globe. We believe that one of the simplest approaches for providing topic information to users joining a chat is keywords. In this paper, we present a method to automatically extract contextually relevant keywords for multi-party live chats. In our work, we identify keywords that are associated with specific ...
متن کامل