Search Query Spell Correction with Weak Supervision in E-commerce

Kakkar, Vishal; Sharma, Chinmay; Pande, Madhura; Kumar, Sanjay

doi:10.18653/v1/2023.acl-industry.66

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Synthetically generating misspellings from correct spellings, rather than extracting misspellingcorrection pairs from some linguistic resources (e.g., query logs), is another common approach to addressing the scarcity of training data for spelling error correction. It is interesting to see that this line of attempts has also emphasized the importance of considering pronunciations in parallel to this work (Wang et al, 2018;Kakkar et al, 2023).…”

Section: Related Workmentioning

confidence: 74%

Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs

Kaji

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

View full text Add to dashboard Cite

Edit distance has been successfully used to extract training data, i.e., misspelling-correction pairs, of spelling correction models from search query logs in languages including English. However, the success does not readily apply to Japanese, where misspellings are often dissimilar to correct spellings due to the romanizationbased input methods. To address this problem, we introduce lattice path edit distance, which utilizes romanization lattices to efficiently consider all possible romanized forms of input strings. Empirical experiments using Japanese search query logs demonstrated that the lattice path edit distance outperformed baseline methods including the standard edit distance combined with an existing transliterator and morphological analyzer. A training data collection pipeline that uses the lattice path edit distance has been deployed in production at our search engine for over a year.

show abstract

Section: Related Workmentioning

confidence: 74%

Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs

Kaji

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

View full text Add to dashboard Cite

show abstract

Spelling Check with Sparse Distributed Representations Learning

Soisoonthorn,

Maliyaem,

Unger

2023

Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval

View full text Add to dashboard Cite

A Survey of Semantic Parsing Techniques

Jiang,

Cai

2024

Symmetry

View full text Add to dashboard Cite

In the information age, semantic parsing technology drives efficiency improvement and accelerates the process of intelligence. However, it faces complex understanding, data inflation, inappropriate evaluation, and difficult application of advanced large models. This study analyses the current challenges and looks forward to the development trend of the technology. Specific approaches include: this study adopts a systematic review method and strictly follows the PRISMA framework, deeply analyzes the key ideas, methods, problems, and solutions of traditional and neural network methods, and explores the model performance, API application, dataset, and evaluation mechanism. Through literature analysis, the technology is classified according to its application scenarios. Then, the practical application contributions are summarized, current limitations such as data size, model performance, and resource requirements are analyzed, and future directions such as dataset expansion, real-time performance enhancement, and industrial applications are envisioned. The results of the study show significant advances in semantic parsing technology with far-reaching impacts. Traditional and neural network methods complement each other to promote theoretical and practical innovation. In the future, with the continuous progress and in-depth application of machine learning technology, semantic parsing technology needs to further deepen the research on logical reasoning and evaluation, to better cope with technical challenges and lead the new development of natural language processing and AI.

show abstract

Search Query Spell Correction with Weak Supervision in E-commerce

Cited by 3 publications

References 0 publications

Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs

Lattice Path Edit Distance: A Romanization-aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs

Spelling Check with Sparse Distributed Representations Learning

A Survey of Semantic Parsing Techniques

Contact Info

Product

Resources

About