ABSTRACT
This study focused on enhancing learning sequences using a method inspired by the brain, following Hawkins's approach. Capable of not only recognizing existing sequences but also learning new ones and ensuring fault-tolerant operations, the learning method was evaluated through a spelling check. The evaluation utilized the standard TREC-5 Confusion Track dataset to automatically correct incorrect words. The new method was compared with other techniques, such as Levenshtein Distance, pyspellchecker, LSTM, and Elmosclstm (Semantically Conditioned LSTM and Elmo Transformer), which is the state-of-the-art. The results demonstrated that the highest accuracy at the word level was 79.35%%, surpassing Elmosclstm's 74.41%. Additionally, at the sentence level, the brain-inspired method achieved 90.75% accuracy, outperforming Elmosclstm's 72.18%.
- M. Bruno and S. Mário. 2004. Spelling correction for search engine queries. In Proceedings of Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science), volume 3230, pages 372–383.Google Scholar
- V. I. Levenshtein. 1965. Binary codes capable of correcting deletions, insertions, and reversals. In Proceedings of Soviet Physics. Doklady, volume 10, pages 707–71.Google Scholar
- F. J. Damerau. 1964. A technique for computer detection and correction of spelling errors. In Proceedings of Communications of the ACM, volume 7, pages 171–176.Google ScholarDigital Library
- H. Shang and T. H. Merrettal. 1996. Tries for approximate string matching. In Proceedings of IEEE Transactions on Knowledge and Data Engineering, volume 8, number 4, pages 540–547, August.Google Scholar
- T. M. Miangah. 2014. FarsiSpell: A spell-checking system for Persian using a large monolingual corpus. In Proceedings of Literary and Linguistic Computing, volume 29, number 1, pages 56–73.Google ScholarCross Ref
- E. Ukkonen. 1985. Algorithms for Approximate String Matching. In Proceedings of Information and Control, volume 64, numbers 1-3, pages 100–118.Google ScholarDigital Library
- Peter Norvig. How to Write a Spelling Corrector. [Online]. Available: https://norvig.com/spell-correct.html.Google Scholar
- T. Barrus. 2018. Pyspellchecker-Pure python spell checker based on work by Peter Norvig. [Online]. Available: https://pypi.org/project/pyspellchecker.Google Scholar
- Sanat Sharma, Josep Valls-Vargas, Tracy Holloway King, Francois Guerin, and Chirag Arora. 2023. Contextual Multilingual Spellchecker for User Queries. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '23). Association for Computing Machinery, New York, NY, USA, 3395–3399.Google ScholarDigital Library
- A. C. Kinaci. 2018. Spelling correction using recurrent neural networks and character level N-gram. In Proceedings of the 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), pages 1–4, Malatya, Turkey.Google ScholarCross Ref
- S. Sooraj, K. Manjusha, M. Kumar, and K. Soman. 2018. Deep learning based spell checker for Malayalam language. In Journal of Intelligent and Fuzzy Systems, volume 34, pages 1427–1434.Google ScholarDigital Library
- I. Sutskever, O. Vinyals, and Q. V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems, volume 4.Google Scholar
- Vishal Kakkar, Chinmay Sharma, Madhura Pande, and Surender Kumar. 2023. Search Query Spell Correction with Weak Supervision in E-commerce. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 687–694, Toronto, Canada. Association for Computational Linguistics.Google ScholarCross Ref
- Ubrangala, Dayananda & Sharma, Juhi & Kondapalli, Ravi & R, Kiran & Agarwala, Amit & Boué, Laurent. 2023. Domain specificity and data efficiency in typo tolerant spell checkers: the case of search in online marketplaces.Google Scholar
- Xiangci Li, Hairong Liu, and Liang Huang. 2020. Context-aware Stand-alone Neural Spelling Correction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 407–414, Online.Google Scholar
- S. M. Jayanthi, D. Pruthi, and G. Neubig. 2020. NeuSpell: A neural spelling correction toolkit. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 158–164.Google Scholar
- Thasayu Soisoonthorn, Herwig Unger, and Maleerat Maliyaem. 2023. Spelling Check: A New Cognition-Inspired Sequence Learning Memory. In Journal of Advances in Information Technology, volume 14, number 3, pages 399–410.Google ScholarCross Ref
- X. Chen, W. Wang, and W. Li. 2012. An overview of Hierarchical Temporal Memory: A new neocortex algorithm. In Proceedings of the 2012 International Conference on Modelling, Identification and Control, pages 1004–1010, Wuhan, China.Google Scholar
- H. Jeff and B. Sandra. 2004. On intelligence. Times Books.Google Scholar
- A. Subutai and H. Jeff. 2015. Properties of sparse distributed representations and their application to hierarchical temporal memory. arXiv.Google Scholar
- P. B. Kantor and E. M. Voorhees. 2000. The TREC-5 confusion track: Comparing retrieval methods for scanned text. In Proceedings of Information Retrieval, volume 2(2/3), pages 165–176.Google Scholar
Index Terms
- Spelling Check with Sparse Distributed Representations Learning
Recommendations
Role of homeostasis in learning sparse representations
Neurons in the input layer of primary visual cortex in primates develop edge-like receptive fields. One approach to understanding the emergence of this response is to state that neural activity has to efficiently represent sensory data with respect to ...
Fast multi-task learning for query spelling correction
CIKM '12: Proceedings of the 21st ACM international conference on Information and knowledge managementIn this paper, we explore the use of a novel online multi-task learning framework for the task of search query spelling correction. In our procedure, correction candidates are initially generated by a ranker-based system and then re-ranked by our multi-...
Thai Word Segmentation with a Brain-Inspired Sparse Distributed Representations Learning Memory
Word segmentation is necessary for many natural language processing, especially Thai language, that is, unsegmented words. However, wrong segmentation causes terrible performance in the final result. In this study, we propose two new brain-inspired ...
Comments