Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval 2017
DOI: 10.1145/3077136.3080664
|View full text |Cite
|
Sign up to set email alerts
|

An Extended Relevance Model for Session Search

Abstract: ABSTRACTe session search task aims at best serving the user's information need given her previous search behavior during the session. We propose an extended relevance model that captures the user's dynamic information need in the session. Our relevance modelling approach is directly driven by the user's query reformulation (change) decisions and the estimate of how much the user's search behavior a ects such decisions. Overall, we demonstrate that, the proposed approach signi cantly boosts session search perfo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
8
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(9 citation statements)
references
References 14 publications
1
8
0
Order By: Relevance
“…Understanding the intended query is crucial to delivering desired results. Prior to the recent AI-based improvements log analysis [4,14] or session based approaches [16,22] were employed to understand searching behavior patterns. Such behaviour was found to differ based on the domain of research, such as in oncology [23] and pandemic diseases [20].…”
Section: Related Workmentioning
confidence: 99%
“…Understanding the intended query is crucial to delivering desired results. Prior to the recent AI-based improvements log analysis [4,14] or session based approaches [16,22] were employed to understand searching behavior patterns. Such behaviour was found to differ based on the domain of research, such as in oncology [23] and pandemic diseases [20].…”
Section: Related Workmentioning
confidence: 99%
“…To answer this question we first need to retrieve the passage about Robert Smith in order to find the name of the company he founded (General Mills), and subsequently retrieve the passage about General Mills, which contains the answer the question (Golden Valley, Minnesota). Even though multi-hop QA requires multiple retrieval hops, it is fundamentally different from session search (Yang et al, 2015;Levine et al, 2017) and conversational search (Dalton et al, 2019;Voskarides et al, 2020;Vakulenko et al, 2021), since in multi-hop QA the information need of the user is expressed in a single question, thus not requiring multiple turns of interaction.…”
Section: Introductionmentioning
confidence: 99%
“…More precisely, the users, for the purpose of satisfying their information seeking goal, could start with a broadly scoped query and then guide the search system to return a more focused set of relevant responses [1]. In a conversational IR workflow, similar to the evolution of information needs within search sessions of standard IR [9,27], an increased user engagement with conversations is likely to facilitate a more focused evolution of the information needs, e.g., a general information need on the planet Uranus can evolve to a question on its peculiarly tilted axis through conversation exchanges between a user and the system [14,15].…”
Section: Introductionmentioning
confidence: 99%