A Theoretical Framework for Conversational Search

By Filip Radlinski, Nick Craswell. Conference on Human Information Interaction and Retrieval, 2017

493 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/ba3659ef1d5835c07ba0de91f61fe8c3611b3bf1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems (2018, background): “Radlinski and Craswell described the basic features of conversational search systems [22].”
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations (2019, background): “Radlinski and Craswell [33] proposed a theoretical framework for conversational search highlighting the need for multi-turn interactions with users for narrowing down their specific information needs.”
Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology (2020, background): “While publications predicting the arrival of conversational interfaces go back at least three decades [6], the widespread adoption of conversational interfaces beyond the confines of task-oriented dialogue systems (TDSs) is a recent development [46].”
MIMICS: A Large-Scale Data Collection for Search Clarification (2020, background): “Recently, it attracted much attention in the information retrieval literature [1, 13, 22, 29, 30].”
Dialog Inpainting: Turning Documents into Dialogs (2022, background): “Conversational question answering systems (ConvQA) (Stede & Schlangen, 2004; Radlinski & Craswell, 2017; Culpepper et al., 2018), would empower users to answer these questions as if they could discuss with an expert at any time.”
Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach (2023, unknown): “When performings these instructions, LLMs act as a traditional recommender .”
A Survey on Conversational Recommender Systems (2020, background): “Generally, conversational recommendation shares a number of similarities with the problem of conversational search, an area that has also received increased interest in recent years [110].”
Towards Conversational Search and Recommendation: System Ask, User Respond (2018, background): “Radlinski and Craswell [26] proposed a theoretical framework for conversational search, which described some basic design philosophies for conversational search systems.”
What Do You Mean Exactly?: Analyzing Clarification Questions in CQA (2017, background): “The ability to ask clariﬁcation questions is one of the key desired components of conversational search systems [9], and can be used for multiple tasks, e.g., to resolve anaphora and coreferences [8].”
Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search (2020, background): “s [11] or human-system interactions with rule-based models [52]. Some early work also focus on spoken conversations in a specific domain, such as travel [3, 22]. More recently, Radlinski and Craswell [42] introduced a theoretical framework and a set of potentially desirable features for a conversati”
From Semantic Retrieval to Conversational Agent: A Web-Based RAG Architecture for Interactive System Dynamics Modeling (2026, unknown): “…on Conversational RAG or Agentic Search, building upon the theoretical frameworks for conversational interaction proposed by Radlinski and Craswell [15], and driven by large-scale evaluation campaigns such as the TREC Conversational Assistance Track (CAsT) [16] and large-scale datasets like ORCAS…”