paper-with-me

Papers

Syntax-based data augmentation for Hungarian-English machine translation

2022-01-18 · Attila Nagy, Patrick Nanys, Balázs Frey Konrád, Bence Bial, Judit Ács

We train Transformer-based neural machine translation models for Hungarian-English and English-Hungarian using the Hunglish2 corpus. Our best models achieve a BLEU score of 40.0 on HungarianEnglish and 33.4 on English-Hungarian. Furthermore, we present results on an ongoing work about syntax-based augmentation for neural machine translation. Both our code and models are publicly available.

📄 PDF Abstract BibTeX arXiv:2201.06876

Code (2)

attilanagy234/syntax-augmentation-nmt 공식 구현 pytorch
attilanagy234/treeswap pytorch

Tasks

Data AugmentationMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Developing neural machine translation models for Hungarian-English

2021-11-07 · Attila Nagy

I train models for the task of neural machine translation for English-Hungarian and Hungarian-English, using the Hunglish2 corpus. The main contribution of this work is evaluating different data augmentation methods duri…

Data AugmentationDependency ParsingMachine TranslationNMT+1

Syntax-aware Data Augmentation for Neural Machine Translation

2020-04-29 · Sufeng Duan, Hai Zhao, Dong-dong Zhang, Rui Wang

Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data. In this paper, we propose a novel data augmentation enhancement strategy for neural m…

Data AugmentationMachine TranslationNMTSentence+1

Light Verb Constructions in the SzegedParalellFX English--Hungarian Parallel Corpus

2012-05-01 · LREC 2012 5 · Veronika Vincze

In this paper, we describe the first English-Hungarian parallel corpus annotated for light verb constructions, which contains 14,261 sentence alignment units. Annotation principles and statistical data on the corpus are …

Machine TranslationRetrievalSentenceTranslation

Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian

2019-08-01 · WS 2019 8 · B{\'a}lint D{\"o}br{\"o}ssy, M{\'a}rton Makrai, Bal{\'a}zs Tarj{\'a}n, Gy{\"o}rgy Szasz{\'a}k

For morphologically rich languages, word embeddings provide less consistent semantic representations due to higher variance in word forms. Moreover, these languages often allow for less constrained word order, which furt…

LemmatizationMorphological AnalysisWord Embeddings

English to Hungarian Morpheme-based Statistical Machine Translation System with Reordering Rules

2013-08-01 · WS 2013 8 · L{\'a}szl{\'o} Laki, Attila Nov{\'a}k, Borb{\'a}la Sikl{\'o}si
Machine TranslationTranslation