Filters








10,966 Hits in 7.0 sec

Vartani Spellcheck – Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance [article]

Aditya Pal, Abhijit Mustafi
2020 arXiv   pre-print
A majority of previously developed language models for error correction of Hindi spelling have been context-free.  ...  We use a lookup dictionary and context-based named entity recognition (NER) for detection of possible spelling errors in the text.  ...  ACKNOWLEDGMENT We are extremely thankful to Google Colaboratory [24] and their powerful hardware which was used to run our BERT models.  ... 
arXiv:2012.07652v1 fatcat:u55lueliknbrhn3m4uvhxrw4qi

A Systematic Literature Review on Spell Checkers for Bangla Language

Prianka Mandal, B M Mainul Hossain
2017 International Journal of Modern Education and Computer Science  
In this paper, we present a systematic literature review on checking and correcting spelling errors in Bangla language.  ...  Spell checkers check whether a word is misspelled and provide suggestions to correct it.  ...  91.37% S4 [17] 13,000 words 90.8% for correcting single error misspellings and 67% for correcting multiple error misspellings S5 [18] 1607 words 98% for correcting single error misspellings  ... 
doi:10.5815/ijmecs.2017.06.06 fatcat:lacngn2x6nd2rbv67hslqy3xlq

Spell corrector for Bangla language using Norvig's algorithm and Jaro-Winkler distance

Istiak Ahamed, Maliha Jahan, Zarin Tasnim, Tajbia Karim, S. M. Salim Reza, Dilshad Ara Hossain
2021 Bulletin of Electrical Engineering and Informatics  
The spelling mistakes are much larger in proportion when it comes to Bangla language. In our paper, we presented a method for error detection and correction in Bangla words' spellings.  ...  Our system could detect a misspelled Bangla word and provide two following services-suggesting correct spellings for the word and correcting the word.  ...  This work has been supported by Department of Information and Communication Technology under Assistant Professor Dr. S M Salim Reza.  ... 
doi:10.11591/eei.v10i4.2410 fatcat:lz4pto3hfvfkfl4mjhx3sufoie

A generalized hidden Markov model with discriminative training for query spelling correction

Yanen Li, Huizhong Duan, ChengXiang Zhai
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
Experiments on two query spelling correction datasets demonstrate that the proposed generalized HMM is effective for correcting multiple types of spelling errors.  ...  algorithm to have access to a better working set of candidate corrections as well as to cover splitting and concatenation errors, which no existing method in academic literature can correct.  ...  center at UIUC, part of CCICADA, and a DHS Center of Excellence.  ... 
doi:10.1145/2348283.2348365 dblp:conf/sigir/LiDZ12 fatcat:hrpefkura5c3rps2mihiwgsaru

Page 88 of Computational Linguistics Vol. 22, Issue 1 [page]

1996 Computational Linguistics  
A Model and a Fast Algorithm for Multiple Errors Spelling Correction. Acta Informatica, 29: 281-302. Gazdar, Gerald and Mellish, Chris. (1989).  ...  A Technique for Computer Detection and Correction of Spelling Errors. Communications of the Association for Computing Machinery, 7(3): 171-176. Du, M. W. and Chang, S. C. (1992).  ... 

State-of-the-Art in Weighted Finite-State Spell-Checking [chapter]

Tommi A. Pirinen, Krister Lindén
2014 Lecture Notes in Computer Science  
are at least as fast as other string algorithms for lookup and error correction.  ...  similar approaches do not provide; 2) Weighted finite-state models have expressive power equal to other, state-of-the-art string algorithms used by contemporary spell-checkers; and 3) Finite-state models  ...  Acknowledgements We thank our fellow researchers in the HFST research group at the University of Helsinki for ideas and discussions.  ... 
doi:10.1007/978-3-642-54903-8_43 fatcat:spsbqbvze5eqdalreucxghqzu4

Survey of Automatic Spelling Correction

Daniel Hládek, Ján Staš, Matúš Pleva
2020 Electronics  
The summary tables show the application area, language, string metrics, and context model for each system.  ...  Our survey selected papers about spelling correction indexed in Scopus and Web of Science from 1991 to 2019. The first group uses a set of rules designed in advance.  ...  Another form of a statistical classifier for the context modeling with multiple models is the Winnow algorithm [96, 103] .  ... 
doi:10.3390/electronics9101670 fatcat:pgf65dpwp5b2xc2hc6xxf5pplm

Parallel Spell-Checking Algorithm Based on Yahoo! N-Grams Dataset [article]

Youssef Bassil
2012 arXiv   pre-print
As a result, spell-checkers will incur low error detection and correction rate and will fail to flag all errors in the text.  ...  Spell-checking is the process of detecting and sometimes providing suggestions for incorrectly spelled words in a text.  ...  Acknowledgment This research was funded by the Lebanese Association for Computational Sciences (LACSC), Beirut, Lebanon under the "Web-Scale Spell-Checking Research Project -WSSCRP2011".  ... 
arXiv:1204.0184v1 fatcat:m6m4t7vf2fgmvii6xcxwzlitra

Synthetic Error Dataset Generation Mimicking Bengali Writing Pattern [article]

Md. Habibur Rahman Sifat, Chowdhury Rafeed Rahman, Mohammad Rafsan, Md. Hasibur Rahman
2020 arXiv   pre-print
The accuracy of any Bengali spell checker or paragraph correction module largely depends on the kind of error dataset it is based on. Manual generation of such error dataset is a cumbersome process.  ...  prone clusters and some rules for Juktakkhar (constant letter clusters) handling while generating errors.  ...  Conclusion In this research, we present a unique algorithm for generating Bengali error words from correct words which can be used for evaluating the performance of various word and context level spell  ... 
arXiv:2003.03484v2 fatcat:fpnwf2k2djc5tpqixypjnrewia

Enhancement of Online Computerized Examination by Incorporating Artificial Intelligence to One Word Answer Questions Along with Multiple Choice Questions

Vimal P., C.K. Kumbharana
2015 International Journal of Computer Applications  
Many hours of examiners and human efforts are required for effective  ...  Today due to the increased number of various courses and increased number of appearing students, the process of examination has become more complex.  ...  does not only perform the error free evaluation but also generates the fast result.  ... 
doi:10.5120/ijca2015907705 fatcat:pac7hrqh65gsbovtp4omojeyjm

Multimodal error correction for speech user interfaces

Bernhard Suhm, Brad Myers, Alex Waibel
2001 ACM Transactions on Computer-Human Interaction  
To extrapolate results from this user study, the article introduces a performance model of (recognition-based) multimodal interaction that predicts input speed including time needed for error correction  ...  Applied to interactive error correction, the model predicts the impact of improvements in recognition technology on correction speeds, and the influence of recognition accuracy and correction method on  ...  Sincere thanks also to all participants of the user studies, to Tanja Schultz and the reviewers for useful suggestions, and to Brinda Ganguly for carefully proofreading the article.  ... 
doi:10.1145/371127.371166 fatcat:evtftvzzkfdztepgmovhxyirca

Fast multi-task learning for query spelling correction

Xu Sun, Anshumali Shrivastava, Ping Li
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
In our procedure, correction candidates are initially generated by a ranker-based system and then re-ranked by our multi-task learning algorithm.  ...  In this paper, we explore the use of a novel online multi-task learning framework for the task of search query spelling correction.  ...  Ahmad and Kondrak [3] propose a method of estimating an error model from query logs using the EM algorithm. Li et al.  ... 
doi:10.1145/2396761.2396800 dblp:conf/cikm/SunSL12 fatcat:rfjko462brglfao5f6vyfpmb44

Hierarchical Attention Transformer Architecture For Syntactic Spell Correction [article]

Abhishek Niranjan, M Ali Basha Shaik, Kushal Verma
2020 arXiv   pre-print
We demonstrate our model on spell correction dataset from Samsung Research, and report significant improvement of 0.11\%, 0.32\% and 0.69\% in character (CER), word (WER) and sentence (SER) error rates  ...  With the motivation of building a reliable and fast post-processing textual module to assist all the text-related use cases in mobile phones, we take on the popular spell correction problem.  ...  ACKNOWLEDGEMENTS We gratefully acknowledge the support from Samsung Research for funding of the research project. We thank Chan Woo Kim and Dhananjaya Gowda for their encouragement and support.  ... 
arXiv:2005.04876v1 fatcat:mb4yt3urfnf2japwrgpfttaepe

A hybrid Technique for Cleaning Missing and Misspelling Arabic Data in Data Warehouse

Mohammed Abdullah Al-Hagery, Department of Computer Science, College of Computer, Qassim University, KSA, Latifah Abdullah Alreshoodi, Maram Abdullah Almutairi, Suha Ibrahim Alsharekh, Emtenan Saad Alkhowaiter
2019 International Journal of Information Technology and Computer Science  
A sample of data before and after cleaning errors presented. of this approach.  ...  This, in turn, leads to discover correct patterns of knowledge and get an accurate Decision-Making. This approach established based on the merging of different algorithms.  ...  Furthermore, a hybrid system based on the confusion matrix and Noisy Channel Spelling Correction Model developed to detect and correct Arabic spelling errors [30] , A spelling error detection and correction  ... 
doi:10.5815/ijitcs.2019.07.03 fatcat:xwc5agcrczfand5ypjojz5w5he

Fast error-tolerant search on very large texts

Marjan Celikik, Holger Bast
2009 Proceedings of the 2009 ACM symposium on Applied Computing - SAC '09  
We combine various ideas from the large body of literature on approximate string searching and spelling correction techniques to a new algorithm for the spelling variants clustering problem that is both  ...  We have integrated our algorithms into the CompleteSearch engine in a way that achieves error-tolerant search without significant blowup in neither index size nor query processing time.  ...  CONCLUSIONS AND FUTURE WORK We have defined the spelling variants clustering problem, and presented a new and very fast algorithm for its solution.  ... 
doi:10.1145/1529282.1529669 dblp:conf/sac/CelikikB09 fatcat:gksr2hzdmjhfhe5ip56jaol6ji
« Previous Showing results 1 — 15 out of 10,966 results