Self-feeding Semi-supervised Training Method for Grammatical Error Correction
- Title
- Self-feeding Semi-supervised Training Method for Grammatical Error Correction
- Authors
- 권순철
- Date Issued
- 2023
- Publisher
- 포항공과대학교
- Abstract
- Grammatical error correction (GEC) has been successful with deep and complex neural machine translation models, but published annotated datasets to train the large models are scarce. In this dissertation, I propose a novel self-feeding training method that generates incorrect sentences from correct sentences. The proposed training method can generate appropriate wrong sentences from unlabeled sentences, using a data generation model trained as an autoencoder. It can also add artificial noise to correct sentences to automatically generate noisy sentences. I show that the GEC models trained with the self-feeding training method are successful without extra annotated data or deeper neural network-based models, achieving F0.5 score of 0.5982 on the CoNLL-2014 Shared Task test data with a transformer model. The results also show that fully unlabeled training is possible for data-scarce domains and languages.
- URI
- http://postech.dcollection.net/common/orgView/200000660074
https://oasis.postech.ac.kr/handle/2014.oak/118226
- Article Type
- Thesis
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.