DC Field | Value | Language |
---|---|---|
dc.contributor.author | 권순철 | - |
dc.date.accessioned | 2023-08-31T16:30:43Z | - |
dc.date.available | 2023-08-31T16:30:43Z | - |
dc.date.issued | 2023 | - |
dc.identifier.other | OAK-2015-10029 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000660074 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/118226 | - |
dc.description | Doctor | - |
dc.description.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. | - |
dc.language | eng | - |
dc.publisher | 포항공과대학교 | - |
dc.title | Self-feeding Semi-supervised Training Method for Grammatical Error Correction | - |
dc.type | Thesis | - |
dc.contributor.college | 컴퓨터공학과 | - |
dc.date.degree | 2023- 2 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.