Context-aware query classification

Cao, Huanhuan; Hu, Derek Hao; Shen, Dong; Jiang, Daxin; Sun, Ju; Chen, Enhong; Yang, Qiang

doi:10.1145/1571941.1571945

Cited by 134 publications

(83 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Web search query classification is an ongoing research challenge that involves the grouping of user queries into specific categories so as to better predict user intent, retrieve the most relevant webpages for the user, and direct web advertisements to the appropriate audiences [23] [59]- [65]. It is estimated that the most popular queries only involve between 2.4 and 2.7 words, making it difficult to disambiguate and pinpoint user intent, due to the small amount of information contained in the queries [23].…”

Section: Search Query Classification and Paid Adsmentioning

confidence: 99%

Web Search Query Privacy, an End-User Perspective

Mivule¹

2017

JIS

View full text Add to dashboard Cite

While search engines have become vital tools for searching information on the Internet, privacy issues remain a growing concern due to the technological abilities of search engines to retain user search logs. Although such capabilities might provide enhanced personalized search results, the confidentiality of user intent remains uncertain. Even with web search query obfuscation techniques, another challenge remains, namely, reusing the same obfuscation methods is problematic, given that search engines have enormous computation and storage resources for query disambiguation. A number of web search query privacy procedures involve the cooperation of the search engine, a nontrusted entity in such cases, making query obfuscation even more challenging. In this study, we provide a review on how search engines work in regards to web search queries and user intent. Secondly, this study reviews material in a manner accessible to those outside computer science with the intent to introduce knowledge of web search engines to enable non-computer scientists to approach web search query privacy innovatively. As a contribution, we identify and highlight areas open for further investigative and innovative research in regards to end-user personalized web search privacy-that is methods that can be executed on the user side without third party involvement such as, search engines. The goal is to motivate future web search obfuscation heuristics that give users control over their personal search privacy.

show abstract

Section: Search Query Classification and Paid Adsmentioning

confidence: 99%

Web Search Query Privacy, an End-User Perspective

Mivule¹

2017

JIS

View full text Add to dashboard Cite

show abstract

“…For instance, queries that are abbreviations and acronyms can be matched to their expanded forms by mining word associations in anchor text from a corpus and query reformulations from query logs [40]. Semantic graphs are commonly used to model word senses and are usually built using thesauri or lexical databases such as WordNet 8 . In these cases, supervised and unsupervised approaches such as PageRank, HITS or node similarity can be used to find alternative queries [24,38].…”

Section: Contextual Query Disambiguation Word Disambiguation Ismentioning

confidence: 99%

Query Suggestion and Data Fusion in Contextual Disambiguation

Shokouhi

Sloan

Bennett

et al. 2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

Queries issued to a search engine are often under-specified or ambiguous. The user's search context or background may provide information that disambiguates their information need in order to automatically predict and issue a more effective query. The disambiguation can take place at different stages of the retrieval process. For instance, contextual query suggestions may be computed and recommended to users on the result page when appropriate, an approach that does not require modifying the original query's results. Alternatively, the search engine can attempt to provide efficient access to new relevant documents by injecting these documents directly into search results based on the user's context.In this paper, we explore these complementary approaches and how they might be combined. We first develop a general framework for mining context-sensitive query reformulations for query suggestion. We evaluate our context-sensitive suggestions against a state-of-the-art baseline using a click-based metric. The resulting query suggestions generated by our approach outperform the baseline by 13% overall and by 16% on an ambiguous query subset.While the query suggestions generated by our approach have higher quality than the existing baselines, we demonstrate that using them naïvely for injecting new documents into search results can lead to inferior rankings. To remedy this issue, we develop a classifier that decides when to inject new search results using features based on suggestion quality and user context. We show that our context-sensitive result fusion approach (Corfu) improves retrieval quality for ambiguous queries by up to 2.92%. Our approaches can efficiently scale to massive search logs, enabling a data-driven strategy that benefits from observing how users issue and reformulate queries in different contexts.

show abstract

“…An illustration of the computational costs for building a suffix tree is reported by Cao et al [36] who draw on query clustering for mining context from query history and click-through data, and by Cao et al [35] who employ click-through data for query classification. These authors show that click-through data is a good source of evidence for query classification and indicate that conditional random fields are an effective statistical model for contextual search.…”

Section: Concluding Remarks and Suggestionsmentioning

confidence: 99%

“…Campbell et al [34] use corpora produced from company intranets. Cao et al [35] use the ACM KDD Cup data set. Chapelle et al [42]'s research work report interleaving as an alternative approach to collecting relevance assessments, since the conventional Cranfield-based approach to evaluation is not free of drawbacks although it is the most used and well accepted in non-contextual search.…”

Section: Concluding Remarks and Suggestionsmentioning

confidence: 99%

Contextual Search: A Computational Framework

Melucci

2012

FNT in Information Retrieval

View full text Add to dashboard Cite

Context-aware query classification

Cited by 134 publications

References 24 publications

Web Search Query Privacy, an End-User Perspective

Web Search Query Privacy, an End-User Perspective

Query Suggestion and Data Fusion in Contextual Disambiguation

Contextual Search: A Computational Framework

Contact Info

Product

Resources

About