Filters








1,446 Hits in 8.0 sec

On Correcting Misspelled Queries in Email Search

Abhijit Bhole, Raghavendra Udupa
2015 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We consider the problem of providing spelling corrections for misspelled queries in Email Search using user's own mail data.  ...  We address the challenge of design- ing an effective spelling correction algorithm for Email Search in the absence of query logs.  ...  Introduction We consider the problem of correcting misspelled user queries in Email Search.  ... 
doi:10.1609/aaai.v29i1.9282 fatcat:da6iqbmtqrb7te5lpskqvpc66y

A Graph Approach to Spelling Correction in Domain-Centric Search

Zhuowei Bao, Benny Kimelfeld, Yunyao Li
2011 Annual Meeting of the Association for Computational Linguistics  
Spelling correction for keyword-search queries is challenging in restricted domains such as personal email (or desktop) search, due to the scarcity of query logs, and due to the specialized nature of the  ...  For that task, this paper presents an algorithm that is based on statistics from the corpus data (rather than the query log).  ...  For example, in email search such a document is an email with a title, a body, one or more recipients, and so on.  ... 
dblp:conf/acl/BaoKL11 fatcat:rpsywsyxebec3f3u4pl57obtxe

Automated Email Answering by Text Pattern Matching [chapter]

Eriks Sneiders
2010 Lecture Notes in Computer Science  
The system works in three languages. The performance was evaluated on two email sets; the main advantage of our email answering technique is good correctness of the delivered replies.  ...  Answering email by standard answers is a common practice at contact centers. Our research assists this process by creating reply messages that contain one or several standard answers.  ...  The research continues in three directions. First, we need to know what makes a good text pattern, what features we should strive to develop.  ... 
doi:10.1007/978-3-642-14770-8_41 fatcat:rpe57xyezrhwtgd42wystrozoq

Investigating the Impacts of Misspellings in Patent Search by Combining Natural Language Tools and Rule-Based Approaches

Davide Russo, Christian Spreafico, Simone Avogadri, Andrea Precorvi
2022 Knowledge  
Among all sources of technical information, patent information is one of the richest and most comprehensive. Knowing how to search in this mass of documents is becoming increasingly crucial.  ...  Finally, an integrated approach combining word and contextual embedding models based on deep learning with a rule-based algorithm based on wild cards and truncation operators is suggested for correcting  ...  Acknowledgments: The tool used to do the tests, in this case, was kindly provided by TRIX srl, a company specializing in the creation of search engines.  ... 
doi:10.3390/knowledge2030029 fatcat:fb4pzsymijhvljhevjjdo4dsd4

Hashing-Based Approaches to Spelling Correction of Personal Names

Raghavendra Udupa, Shaishav Kumar
2010 Conference on Empirical Methods in Natural Language Processing  
We propose two hashing-based solutions to the problem of fast and effective personal names spelling correction in People Search applications.  ...  We show that both methods give excellent retrieval performance in comparison to several baselines on two lists of misspelled personal names.  ...  However, query logs are not available in some applications (e.g. Email address book search).  ... 
dblp:conf/emnlp/UdupaK10 fatcat:v7oe5sq73zaobalf42ewidhz3m

PeerCollaboration [chapter]

Thomas Bocek, Burkhard Stiller
2009 Lecture Notes in Computer Science  
Typical tasks in PeerCollaboration are searching, retrieving, creating, changing, and maintaining documents in a collaborative manner. Three problem areas are investigated within this system.  ...  The first problem focuses on similarity search on top of existing P2P networks and highlights a novel algorithm, which outperforms compared approaches.  ...  a misspelled search query, and provides decentralized control for managing changes.  ... 
doi:10.1007/978-3-642-02627-0_17 fatcat:cgyjgvicpfdhxezxvabhbavdmu

Spelling Correction as a Foreign Language [article]

Yingbo Zhou, Utkarsh Porwal, Roberto Konow
2019 arXiv   pre-print
In this paper, we reformulated the spell correction problem as a machine translation task under the encoder-decoder framework.  ...  misspelling and correct spelled query pair.  ...  Related Work Spelling correction is used in wide range of applications other than Web search and e-commerce search such as personal search in email Gupta et al. (2019) to improve healthcare inquiries  ... 
arXiv:1705.07371v2 fatcat:4is2exy6jzai7h4xghv4bytvgq

Web Text Corpus for Natural Language Processing

Vinci Liu, James R. Curran
2006 Conference of the European Chapter of the Association for Computational Linguistics  
We show that for context-sensitive spelling correction the Web Corpus results are better than using a search engine.  ...  With many more words available on the web, better results can be obtained by collecting much larger web corpora.  ...  In the context-sensitive spelling correction task, a simple memory-based learner trained on our Web Corpus achieved better results than method based on search engine queries.  ... 
dblp:conf/eacl/LiuC06 fatcat:opmtp4ifobav5g52a7mhacfbhq

Spelling Correction with Denoising Transformer [article]

Alex Kuznetsov, Hector Urdiales
2021 arXiv   pre-print
We present a novel method of performing spelling correction on short input strings, such as search queries or individual words.  ...  This procedure is used to train the production spelling correction model based on a transformer architecture. This model is currently served in the HubSpot product search.  ...  This leads to 10-15% of web search queries being misspelled (Dalianis, 2002; Cucerzan and Brill, 2004) , with percentage of misspellings increasing to up to 20% for long-tail queries (Broder et al.,  ... 
arXiv:2105.05977v1 fatcat:utgqze55lncojepfrfykofbnse

AQUA: an Advanced QUery Architecture for the SPARC Portal

Niloofar Shahidi, Xuanzhi Lin, Yuda Munarko, Laila Rasmy, Tram Ngo
2021 F1000Research  
SPARC search engine.  ...  Currently, the SPARC Portal provides a primary search tool, which lacks some features to improve the search experience.  ...  Table 2 shows that AQUA performs better in correcting misspellings that appear in a two-term "author" query.  ... 
doi:10.12688/f1000research.73018.1 fatcat:puvhq5cuxndjje6n6tke43ierq

A "Suggested" Picture of Web Search in Turkish

Erdem Sarigil, Oguz Yilmaz, Ismail Sengor Altingovde, Rifat Ozcan, ÖzgÜr Ulusoy
2016 ACM Transactions on Asian and Low-Resource Language Information Processing  
A "suggested" picture of Web search in Turkish.  ...  CCS Concepts: r Information systems → Web searching and information discovery; Web log analysis Additional Key Words and Phrases: Turkish query characteristics, query spelling correction ACM Reference  ...  -Turker and Bitirim [2015] compiled a set of 60 queries that include 30 frequently misspelled terms from the Web and their correct forms.  ... 
doi:10.1145/2891105 fatcat:qhdligipqre3zhsie3ysvkh7s4

Best faces forward

Ido Guy, Sigalit Ur, Inbal Ronen, Sara Weber, Tolga Oral
2012 Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems - CHI '12  
This paper presents Faces, an application built to enable effective people search in the enterprise.  ...  Our study is primarily based on an analysis of the Faces query log over a period of more than four months, with over a million queries and tens of thousands of users.  ...  After clicking the string, users can identify by searching for themselves and clicking on the correct result.  ... 
doi:10.1145/2207676.2208310 dblp:conf/chi/GuyURWO12 fatcat:ml5e6m5e4zaufbkszjlujozl4e

A Secure and Dynamic Fuzzy Multi-Keyword Ranked Search over Encrypted Cloud Data Without Access Pattern Leakage

An-ni CAO
2018 DEStech Transactions on Computer Science and Engineering  
In this paper, we present a secure symmetric searchable encryption scheme without access pattern leakage, based on Fu's scheme.  ...  Recent years, Searchable Encryption (SE) has become one of the hottest topics in cloud computing, because of its flexibility and availability.  ...  the correct one, measured by the Euclidean distance.  ... 
doi:10.12783/dtcse/wcne2017/19820 fatcat:lwbce62ouvbsbhcvwpiwkgnsf4

GABAagent: a system for integrating data on GABA receptors

A. Rachedi, M. Rebhan, H. Xue
2000 Bioinformatics  
The first is a search engine possessing intelligent query reformulation support (GABAengine), the second an elaborate email alert service was designed into the system (GABAalert).  ...  GABAagent relies on server-side flat-file databases that have been created through data mining from Internet sources such as the PubMed, DDBJ, SWISS-PROT and TrEMBL, in addition to the many World Wide  ...  Fig. 4 . 4 Query reformulation support for a search query that contained a misspelled keyword; 'muttatiom LND brain'.  ... 
doi:10.1093/bioinformatics/16.4.301 pmid:10869028 fatcat:vcycseb275cs5cc7kwpe4nvwz4

An Ensemble Method for Spelling Correction in Consumer Health Questions

Halil Kilicoglu, Marcelo Fiszman, Kirk Roberts, Dina Demner-Fushman
2015 AMIA Annual Symposium Proceedings  
In this paper, we propose a method that combines techniques based on edit distance and frequency counts with a contextual similarity-based method for detecting and correcting orthographic errors, including  ...  misspellings, word breaks, and punctuation errors.  ...  [7] focus on spelling correction in the PubMed search engine.  ... 
pmid:26958208 pmcid:PMC4765565 fatcat:koal4byburagrclp26isjlkchm
« Previous Showing results 1 — 15 out of 1,446 results