Sequence Tagging-based Grammatical Error Correction System
(Redirected from GEC sequence tagging model)
Jump to navigation
Jump to search
A Sequence Tagging-based Grammatical Error Correction System is a grammatical error correction system that applies a sequence tagging-based GEC algorithm (that performs sequence tagging of text sequences).
- Example(s):
- GECToR,
- LaserTagger,
- Lex-POS,
- PIE-GEC.
- …
- Counter-Example(s):
- See: Seq2Seq Neural Network, Natural Language Processing System, Encoder-Decoder Neural Network, POS Tagger.
References
2020b
- (Omelianchuk et al., 2020) ⇒ Kostiantyn Omelianchuk, Vitaliy Atrasevych, Artem N. Chernodub, and Oleksandr Skurzhanskyi. (2020). “GECToR - Grammatical Error Correction: Tag, Not Rewrite.” In: Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications (BEA@ACL 2020).
- QUOTE: We develop custom g-transformations: token-level edits to perform (g)rammatical error corrections. Predicting g-transformations instead of regular tokens improves the generalization of our GEC sequence tagging system.
2019
- (Malmi et al., 2019) ⇒ Eric Malmi, Sebastian Krause, Sascha Rothe, Daniil Mirylenka, and Aliaksei Severyn. (2019). “Encode, Tag, Realize: High-Precision Text Editing.” In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019).