Online spelling correction for query completion

Duan, Huizhong; Hsu, Bo-June

doi:10.1145/1963405.1963425

Cited by 88 publications

(35 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In baseline speller we use a substring-based error model P dist (q 0 → q 1 ) described in (Brill and Moore, 2000), the error model training method and the hypotheses generator are similar to (Duan and Hsu, 2011). For building language (P LM ) and error (P dist ) models, we use words collected from the 6-months query log of a commercial search engine.…”

Section: Baseline Speller Setupmentioning

confidence: 99%

Improved Iterative Correction for Distant Spelling Errors

Gubanov¹,

Galinskaya

Baytin

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

show abstract

Section: Baseline Speller Setupmentioning

confidence: 99%

Improved Iterative Correction for Distant Spelling Errors

Gubanov¹,

Galinskaya

Baytin

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

show abstract

“…An alternative technique is to apply a fuzzy completion algorithm, such as the one described by Duan and Hsu [10]. In short, after adding the root node to a priority queue, iteratively add the children of the best path to the queue, applying a penalty as determined by a weighted transformation function if the character sequence of the child node does not match the input prefix.…”

Section: Discussionmentioning

confidence: 99%

Space-efficient data structures for Top- k completion

Hsu

Ottaviano

2013

Proceedings of the 22nd International Conference on World Wide Web

Self Cite

View full text Add to dashboard Cite

Virtually every modern search application, either desktop, web, or mobile, features some kind of query auto-completion. In its basic form, the problem consists in retrieving from a string set a small number of completions, i.e. strings beginning with a given prefix, that have the highest scores according to some static ranking. In this paper, we focus on the case where the string set is so large that compression is needed to fit the data structure in memory. This is a compelling case for web search engines and social networks, where it is necessary to index hundreds of millions of distinct queries to guarantee a reasonable coverage; and for mobile devices, where the amount of memory is limited.We present three different trie-based data structures to address this problem, each one with different space/time/ complexity trade-offs. Experiments on large-scale datasets show that it is possible to compress the string sets, including the scores, down to spaces competitive with the gzip'ed data, while supporting efficient retrieval of completions at about a microsecond per completion.

show abstract

“…For evaluation, Mean Reciprocal Rank (MRR) [8] has become the de facto measure [6]. As cited by Cai and de Rijke [6] and Hofmann et al [17], other approaches -such as a keystroke-based measure [12], for example -have also been considered. Use of anchor text instead of historical queries was explored for the purpose of query renement by Kra and Zien [21].…”

Section: Related Workmentioning

confidence: 99%

Large-scale Generative Query Autocompletion

Maxwell¹,

Bailey²,

Hawking³

2017

Proceedings of the 22nd Australasian Document Computing Symposium

View full text Add to dashboard Cite

ABSTRACTery Autocompletion (QAC) systems are interactive tools that assist a searcher in entering a query, given a partial query prex. Existing QAC research -with a number of notable exceptionsrelies upon large existing query logs from which to extract historical queries. ese queries are then ordered by some ranking algorithm as candidate completions, given the query prex. Given the numerous search environments (e.g. enterprises, personal or secured data repositories) in which large query logs are unavailable, the need for synthetic -or generative -QAC systems will become increasingly important. Generative QAC systems may be used to augment traditional query-based approaches, and/or entirely replace them in certain privacy sensitive applications. Even in commercial Web search engines, a signicant proportion (up to 15%) of queries issued daily have never been seen previously, meaning there will always be opportunity to assist users in formulating queries which have not occurred historically. In this paper, we describe a system that can construct generative QAC suggestions within a user-acceptable timeframe (⇠58ms), and report on a series of experiments over three publicly available, large-scale question sets that investigate dierent aspects of the system's performance.

show abstract

Online spelling correction for query completion

Cited by 88 publications

References 10 publications

Improved Iterative Correction for Distant Spelling Errors

Improved Iterative Correction for Distant Spelling Errors

Space-efficient data structures for Top- k completion

Large-scale Generative Query Autocompletion

Contact Info

Product

Resources

About