An Extended Relevance Model for Session Search

Levine, Nir; Roitman, Haggai; Cohen, Doron

doi:10.1145/3077136.3080664

Cited by 14 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

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%

NeuroBoun: An inquiry-based approach for exploring scientific literature -- a use case in neuroscience

Uskudarli¹,

Gökdeniz²,

Canbeyli³

2020

Preprint

View full text Add to dashboard Cite

Online scientific publications provide vast opportunities for researchers. Alas, the quantity and the rate of increase in the articles make the utilization of these resources very challenging. This work presents as inquirybased approach to support the articulation of complex inter-related queries to gain insights regarding how these subjects have been studied in conjunction with one another as reported in the scientific literature. For this purpose we introduce inquiries that represent inter-related subqueries that are of interest to a researcher. The inquiries are expanded to better capture the intent of the inquirer, from which several queries are generated that represent various juxtapositions of the subjects in consideration. The sets of queries are used to search repositories to yield results that reveal quantitative and temporal relations among the subjects of the inquiry. A web-based tool, NeuroBoun, is developed as a proof of concept for medical publications found in PubMed. A use case related to the asymmetry of amygdala is presented to illustrate the potentials of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

NeuroBoun: An inquiry-based approach for exploring scientific literature -- a use case in neuroscience

Uskudarli¹,

Gökdeniz²,

Canbeyli³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…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%

Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering

Sidiropoulos

Voskarides²,

Vakulenko

et al. 2021

Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing

View full text Add to dashboard Cite

In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop QA, where aggregating information from multiple pieces of information and reasoning over them is required. Despite their success, dense retrieval methods are computationally intensive, requiring multiple GPUs to train. In this work, we introduce a hybrid (lexical and dense) retrieval approach that is highly competitive with the state-of-the-art dense retrieval models, while requiring substantially less computational resources. Additionally, we provide an in-depth evaluation of dense retrieval methods on limited computational resource settings, something that is missing from the current literature.

show abstract

“…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%

Effective Query Formulation in Conversation Contextualization: A Query Specificity-based Approach

Pal

Ganguly

2021

Proceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval

View full text Add to dashboard Cite

Proactively retrieving relevant information to contextualize conversations has potential applications in better understanding the conversational content between communicating parties. Since in contrast to traditional IR, there is no explicitly formulated userquery, an important research challenge is to first identify the candidate segments of text that may require contextualization for a better comprehension of their content, and then make use of these identified segments to formulate a query and eventually retrieve the potentially relevant information to augment a conversation. In this paper, we propose a generic unsupervised framework that involves shifting overlapping windows of terms through a conversation and estimating scores indicating the likelihood of the existence of an information need within these segments. Within our proposed framework, we investigate a query performance prediction (QPP) based approach for scoring these candidate term windows with the hypothesis that a term window that indicates a higher specificity is likely to be indicative of a potential information need requiring contextualization. Our experiments revealed that the QPP approaches of scoring the term windows provide better contextualization than other term extraction approaches. A post-retrieval QPP approach was observed to yield better results than a pre-retrieval one.

show abstract

An Extended Relevance Model for Session Search

Cited by 14 publications

References 14 publications

NeuroBoun: An inquiry-based approach for exploring scientific literature -- a use case in neuroscience

NeuroBoun: An inquiry-based approach for exploring scientific literature -- a use case in neuroscience

Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering

Effective Query Formulation in Conversation Contextualization: A Query Specificity-based Approach

Contact Info

Product

Resources

About