Conversational Information Seeking

Zamani, Hamed; Trippas, Johanne R.; Dalton, Jeff; Radlinski, Filip

doi:10.48550/arxiv.2201.08808

Cited by 14 publications

(15 citation statements)

References 254 publications

(411 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4.1.2 Verbose Query Retrieval. Given the similarity of recommendation and search [7,14,28,86] and the interchangeable nature of filtering profiles and queries, we next examine relevant work in information retrieval. Retrieval with verbose natural language queries has attracted much attention [31], yet the definition of a verbose query differs across retrieval contexts.…”

Section: Research Contextmentioning

confidence: 99%

On Natural Language User Profiles for Transparent and Scrutable Recommendation

Radlinski,

Balog,

Diaz

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years. We focus on the challenge of supporting people's understanding and control of these systems and explore a fundamentally new way of thinking about representation of knowledge in recommendation and personalization systems. Specifically, we argue that it may be both desirable and possible for algorithms that use natural language representations of users' preferences to be developed. We make the case that this could provide significantly greater transparency, as well as affordances for practical actionable interrogation of, and control over, recommendations. Moreover, we argue that such an approach, if successfully applied, may enable a major step towards systems that rely less on noisy implicit observations while increasing portability of knowledge of one's interests.

show abstract

Section: Research Contextmentioning

confidence: 99%

On Natural Language User Profiles for Transparent and Scrutable Recommendation

Radlinski,

Balog,

Diaz

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Conversational information access refers to a subset of task-oriented dialogue systems aimed at supporting users in fulfilling informationseeking goals via multi-turn conversations [53]. It includes the tasks of conversational search, QA, and conversational recommendations [52]. Commercial products, like Amazon's Alexa, Google Assistant, Apple's Siri, Microsoft's XiaoIce, are assisting users in undertaking specific tasks in restricted domains, like restaurant reservations and music recommendation.…”

Section: Conversational Information Accessmentioning

confidence: 99%

Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems

Zhang,

Wang,

Balog

2022

Preprint

View full text Add to dashboard Cite

User simulation has been a cost-effective technique for evaluating conversational recommender systems. However, building a humanlike simulator is still an open challenge. In this work, we focus on how users reformulate their utterances when a conversational agent fails to understand them. First, we perform a user study, involving five conversational agents across different domains, to identify common reformulation types and their transition relationships. A common pattern that emerges is that persistent users would first try to rephrase, then simplify, before giving up. Next, to incorporate the observed reformulation behavior in a user simulator, we introduce the task of reformulation sequence generation: to generate a sequence of reformulated utterances with a given intent (rephrase or simplify). We develop methods by extending transformer models guided by the reformulation type and perform further filtering based on estimated reading difficulty. We demonstrate the effectiveness of our approach using both automatic and human evaluation. CCS CONCEPTS• Information systems → Users and interactive retrieval.

show abstract

“…An area related to CRS is conversational search systems [74,80]. Research work in this area tend to focus on resolving ambiguity in natural language [12,59,79], on open-domain large-scale document retrieval [11,29,60,61], and often do not to utilize historic user-item interactions [28,40,67].…”

Section: Related Work 21 Conversational Recommendation Systemsmentioning

confidence: 99%

Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference

Zhang¹,

Li²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Conversational recommendation system (CRS) is emerging as a user-friendly way to capture users' dynamic preferences over candidate items and attributes. Multi-shot CRS is designed to make recommendations multiple times until the user either accepts the recommendation or leaves at the end of their patience. Existing works are trained with reinforcement learning (RL), which may suffer from unstable learning and prohibitively high demands for computing. In this work, we propose a simple and efficient CRS, MInimalist Non-reinforced Interactive COnversational Recommender Network (Minicorn). Minicorn models the epistemic uncertainty of the estimated user preference and queries the user for the attribute with the highest uncertainty. The system employs a simple network architecture and makes the query-vs-recommendation decision using a single rule. Somewhat surprisingly, this minimalist approach outperforms state-of-the-art RL methods on three realworld datasets by large margins. We hope that Minicorn will serve as a valuable baseline for future research.

show abstract

Conversational Information Seeking

Cited by 14 publications

References 254 publications

On Natural Language User Profiles for Transparent and Scrutable Recommendation

On Natural Language User Profiles for Transparent and Scrutable Recommendation

Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems

Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference

Contact Info

Product

Resources

About