4/18/2023 0 Comments German grammar wikipediaUsing a multilayer convolutional encoder-decoder neural network GEC approach (Chollampatt and Ng, 2018), we evaluate the contribution of Wikipedia edits and find that carefully selected Wikipedia edits increase performance by over 5%.German declension is the paradigm that German uses to define all the ways articles, adjectives and sometimes nouns can change their form to reflect their role in the sentence: subject, object, etc. We extend the automatic error annotation tool ERRANT (Bryant et al., 2017) for German and use it to analyze both gold GEC corrections and Wikipedia edits (Grundkiewicz and Junczys-Dowmunt, 2014) in order to select as additional training data Wikipedia edits containing grammatical corrections similar to those in the gold corpus. %X We develop a grammatical error correction (GEC) system for German using a small gold GEC corpus augmented with edits extracted from Wikipedia revision history. %I Association for Computational Linguistics %S Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text %T Using Wikipedia Edits in Low Resource Grammatical Error Correction Using a multilayer convolutional encoder-decoder neural network GEC approach (Chollampatt and Ng, 2018), we evaluate the contribution of Wikipedia edits and find that carefully selected Wikipedia edits increase performance by over 5%. We develop a grammatical error correction (GEC) system for German using a small gold GEC corpus augmented with edits extracted from Wikipedia revision history. Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated TextĪssociation for Computational Linguistics Using Wikipedia Edits in Low Resource Grammatical Error Correction Cite (Informal): Using Wikipedia Edits in Low Resource Grammatical Error Correction (Boyd, WNUT 2018) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Code = "Using. Association for Computational Linguistics. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, pages 79–84, Brussels, Belgium. Using Wikipedia Edits in Low Resource Grammatical Error Correction. Anthology ID: W18-6111 Volume: Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text Month: November Year: 2018 Address: Brussels, Belgium Venue: WNUT SIG: Publisher: Association for Computational Linguistics Note: Pages: 79–84 Language: URL: DOI: 10.18653/v1/W18-6111 Bibkey: boyd-2018-using Cite (ACL): Adriane Boyd. Abstract We develop a grammatical error correction (GEC) system for German using a small gold GEC corpus augmented with edits extracted from Wikipedia revision history.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |