A Theoretical Framework for Conversational Search

@article{Radlinski2017ATF,
  title={A Theoretical Framework for Conversational Search},
  author={Filip Radlinski and Nick Craswell},
  journal={Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval},
  year={2017}
}
  • Filip Radlinski, Nick Craswell
  • Published 2017
  • Computer Science
  • Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval
This paper studies conversational approaches to information retrieval, presenting a theory and model of information interaction in a chat setting. In particular, we consider the question of what properties would be desirable for a conversational information retrieval system so that the system can allow users to answer a variety of information needs in a natural and efficient manner. We study past work on human conversations, and propose a small set of properties that taken together could… Expand
Knowledge-based Conversational Search
TLDR
This thesis lays foundations for designing conversational search systems by analyzing the requirements and proposing concrete solutions for automating some of the basic components and tasks that such systems should support. Expand
Theories of Conversation for Conversational IR
TLDR
This article summarizes some salient past work on social norms; structures; and affect, prosody, and style; and examines social communication theories briefly as a review to see what has learned about how humans interact with each other and how that might pertain to agents and robots. Expand
Conversational Browsing
TLDR
Analysis and automated support is provided for a type of information-seeking strategy that is effective when the clarity of the information need and familiarity with the collection content are low and can complement query-based information retrieval approaches. Expand
Conceptualizing agent-human interactions during the conversational search process
TLDR
This paper develops a conceptual framework of the actions and intents of users and agents explaining how these actions enable the user to explore the search space and resolve their information need. Expand
Conversational Strategies:
Conversational search relies on an interactive, natural language exchange between a user, who has an information need, and a search system, which elicits and reveals information. Prior researchExpand
Conversational Information Retrieval for Instructional Content – A Modeling Framework and an Implementation for Recipe Search
As commercial voice agents are becoming increasingly popular, conversational search is brought into focus. Being an emerging area of research, there are a lot of questions that remain unanswered. InExpand
Exploring Conversational Search With Humans, Assistants, and Wizards
Chatbots and conversational assistants are becoming increasingly popular. However, for information seeking scenarios, these systems still have very limited conversational abilities, and primarilyExpand
Attentive Memory Networks: Efficient Machine Reading for Conversational Search
TLDR
This paper argues that the process of building a representation of the conversation can be framed as a machine reading task, where an automated system is presented with a number of statements about which it should answer questions and presents the Attentive Memory Network, an end-to-end trainable machine reading algorithm. Expand
Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Dataset
Conversational search is an approach to information retrieval (IR), where users engage in a dialogue with an agent in order to satisfy their information needs. Previous conceptual work describedExpand
Conversations with Search Engines
In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language,Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
Cases, scripts, and information-seeking strategies: On the design of interactive information retrieval systems
TLDR
This paper proposes a model of information retrieval system design based on the ideas of a multidimensional space of information-seeking strategies; dialogue structures for information seeking; cases of specific information- seeking dialogues; anti, scripts as distinguished prototypical cases; and demonstrates the use of the MERIT system, a prototype information retrieved system that incorporates these design principles. Expand
An Evidential Model for Tracking Initiative in Collaborative Dialogue Interactions
TLDR
An evidential model for tracking shifts in both types of initiatives in collaborative dialogue interactions is presented and how this initiative tracking model may be employed by a dialogue system to enable the system to tailor its responses to user utterances based on application domain, system's role in the domain, dialogue history, and user characteristics is shown. Expand
Mixed Initiative in Dialogue: An Investigation into Discourse Segmentation
TLDR
A set of rules for the transfer of control is applied to 4 sets of dialogues and it is found that both allocation of control and the manner in which control is transferred is radically different for the two dialogue types. Expand
Incremental Dialogue Understanding and Feedback for Multiparty, Multimodal Conversation
TLDR
An implemented system for engaging in multiparty dialogue, including incremental understanding and a range of feedback, is described, and an FML message extension for feedback in multipary dialogue that can be connected to a feedback realizer is presented. Expand
“User revealment”—a comparison of initial queries and ensuing question development in online searching and in human reference interactions
TLDR
This paper compares user’s opening queries and their search progression in two sets of data: logs of end-user online searches and user-librarian reference interactions, and applies a communication model to explain how users are induced to reveal their search intention in the dialogue with the intermediary. Expand
Optimizing the turn-taking behavior of task-oriented spoken dialog systems
TLDR
The Finite-State Turn-Taking Machine (FSTTM) is described, a decision-theoretic model that combines data-driven machine learning methods and a cost structure derived from Conversation Analysis to control the turn-taking behavior of dialog systems. Expand
Conversation as Action Under Uncertainty
TLDR
This work proposes a task independent, multimodal architecture for supporting robust continuous spoken dialog called Quartet, and introduces four interdependent levels of analysis and describes representations, inference procedures, and decision strategies for managing uncertainties within and between the levels. Expand
The Dialog State Tracking Challenge
TLDR
The dialog state tracking challenge seeks to address this by providing a heterogeneous corpus of 15K human-computer dialogs in a standard format, along with a suite of 11 evaluation metrics, and shows that the suite of performance metrics cluster into 4 natural groups. Expand
ELIZA—a computer program for the study of natural language communication between man and machine
TLDR
A discussion of some psychological issues relevant to the ELIZA approach as well as of future developments concludes the paper. Expand
MIXED INITIATIVE INTERACTION
Publisher Summary This chapter explains the importance of attending to the dynamics of the interaction when designing knowledge-based systems. Small changes in these dynamics can greatly alter theExpand
...
1
2
3
4
5
...