paper-with-me

Papers

Grammatical Error Generation Based on Translated Fragments

2021-04-20 · NoDaLiDa 2021 5 · Eetu Sjöblom, Mathias Creutz, Teemu Vahtola

We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction. Our method aims at simulating mistakes made by second language learners, and produces a wider range of non-native style language in comparison to state-of-the-art synthetic data creation methods. In addition to purely grammatical errors, our approach generates other types of errors, such as lexical errors. We perform grammatical error correction experiments using neural sequence-to-sequence models, and carry out quantitative and qualitative evaluation. A model trained on data created using our proposed method is shown to outperform a baseline model on test data with a high proportion of errors.

📄 PDF Abstract BibTeX arXiv:2104.09933

Code (0)

등록된 구현이 없습니다.

Tasks

Grammatical Error CorrectionMachine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

Artificial Error Generation with Machine Translation and Syntactic Patterns

2017-07-17 · WS 2017 9 · Marek Rei, Mariano Felice, Zheng Yuan, Ted Briscoe

Shortage of available training data is holding back progress in the area of automated error detection. This paper investigates two alternative methods for artificially generating writing errors, in order to create additi…

Grammatical Error DetectionMachine TranslationTranslation

Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors

2012-07-01 · WS 2012 7 · Rudolf Rosa, Ond{\v{r}}ej Du{\v{s}}ek, David Mare{\v{c}}ek, Martin Popel
Machine TranslationMorphological Inflection

Language CoLLAGE: Grammatical Description with the LinGO Grammar Matrix

2014-05-01 · LREC 2014 5 · Emily M. Bender

Language CoLLAGE is a collection of grammatical descriptions developed in the context of a grammar engineering graduate course with the LinGO Grammar Matrix. These grammatical descriptions include testsuites in well-form…

Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction

2016-06-01 · Duc Tam Hoang, Shamil Chollampatt, Hwee Tou Ng

Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners. The statistical machine translation (SMT) approach to GEC, in which sentences wr…

Grammatical Error CorrectionMachine TranslationTranslation

Evaluation of NMT-Assisted Grammar Transfer for a Multi-Language Configurable Data-to-Text System

2025-01-27 · Andreas Madsack, Johanna Heininger, Adela Schneider, Ching-Yi Chen 외

One approach for multilingual data-to-text generation is to translate grammatical configurations upfront from the source language into each target language. These configurations are then used by a surface realizer and in…

Data-to-Text GenerationMachine TranslationNMTText Generation+1