User interactions with everyday applications as context for just-in-time information access

Budzik, Jay; Hammond, Kristian J.

doi:10.1145/325737.325776

Cited by 154 publications

(101 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first method has λ = ∞ and is therefore noted RQ(∞) -it only uses explicit query keywords, with no refinement. The second one refines explicit queries using the method of the Watson system [8], with λ = 0, hence noted RQ(0). The third method has λ = 1 and is noted RQ(1) -this is the novel method proposed here, which expands the query with keywords from the conversation fragment based on their topical similarity to the query.…”

Section: Resultsmentioning

confidence: 99%

“…Other previous techniques have attempted to use the local context of users' activities, without requiring user interaction [1,8]. However, as we will show, these are less suitable for a conversational environment, because of the nature of the vocabulary and the errors introduced by the ASR such as 'recap', 'sleek' and 'snowman' in this example.…”

Section: Introductionmentioning

confidence: 94%

“…On the contrary, our overall goal is to estimate users' information needs from their explicit queries as discretely as possible. Moreover, using the local context for query refinement instead of external, non-contextual resources has the potential to improve retrieval results [8].…”

Section: Related Workmentioning

confidence: 99%

“…However, the content of the activities itself was not used as a feature. The WATSON system [8] refined explicit queries by concatenating them with keywords extracted from the documents being edited or viewed by the user. However, in order to apply this method to a retrieval system for which the local context is a conversation, the keyword lists must avoid considering irrelevant topics from ASR errors.…”

Section: Related Workmentioning

confidence: 99%

“…If λ = ∞, the refined query is the same as the initial explicit query (with no refinement). By setting λ to 0, the query is like the one used in the Watson system [8], giving the same weight to the query words and to the keywords representing the local context. Because the keywords are related to topics that have various relevance values to the explicit query, we will set the intermediate value λ = 1 in our experiments, to weigh each keyword based on its relevance to the topics of the query.…”

Section: Content-based Query Refinementmentioning

confidence: 99%

See 4 more Smart Citations

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Habibi

Popescu-Belis

2015

Natural Language Processing and Information Systems

View full text Add to dashboard Cite

Abstract. This paper introduces a query refinement method applied to queries asked by users during a meeting or a conversation. Current approaches suffer from poor quality to achieve this goal, but we argue that their performance could be improved by focusing on the local context of the conversation. The proposed technique first represents the local context by extracting keywords from the transcript of the conversation. It then expands the queries with keywords that best represent the topic of the query (e.g. pairs of expansion keywords together with a weight indicating their topical similarity to the query). Moreover, we present a dataset called AREX and an evaluation metric. We compared our query expansion approach with other methods, on topics extracted from the AREX dataset and based on relevance judgments collected in a crowdsourcing experiment. The comparisons indicate the superiority of our method on both manual and ASR transcripts of the AMI Meeting Corpus.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Content-based Query Refinementmentioning

confidence: 99%

See 3 more Smart Citations

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Habibi

Popescu-Belis

2015

Natural Language Processing and Information Systems

View full text Add to dashboard Cite

show abstract

Artificial Intelligence

Buchanan

Leake

2005

Van Nostrand's Scientific Encyclopedia

View full text Add to dashboard Cite

show abstract

Evaluation of context‐aware recommendation systems for information re‐finding

Sappelli

Verberne

Kraaij

2016

Asso for Info Science & Tech

View full text Add to dashboard Cite

In this article we evaluate context‐aware recommendation systems for information re‐finding by knowledge workers. We identify 4 criteria that are relevant for evaluating the quality of knowledge worker support: context relevance, document relevance, prediction of user action, and diversity of the suggestions. We compare 3 different context‐aware recommendation methods for information re‐finding in a writing support task. The first method uses contextual prefiltering and content‐based recommendation (CBR), the second uses the just‐in‐time information retrieval paradigm (JITIR), and the third is a novel network‐based recommendation system where context is part of the recommendation model (CIA). We found that each method has its own strengths: CBR is strong at context relevance, JITIR captures document relevance well, and CIA achieves the best result at predicting user action. Weaknesses include that CBR depends on a manual source to determine the context and in JITIR the context query can fail when the textual content is not sufficient. We conclude that to truly support a knowledge worker, all 4 evaluation criteria are important. In light of that conclusion, we argue that the network‐based approach the CIA offers has the highest robustness and flexibility for context‐aware information recommendation.

show abstract

User interactions with everyday applications as context for just-in-time information access

Cited by 154 publications

References 8 publications

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Artificial Intelligence

Evaluation of context‐aware recommendation systems for information re‐finding

Contact Info

Product

Resources

About