What Level of Quality Can Neural Machine Translation Attain on Literary Text?

Toral, Antonio; Way, Andy

doi:10.1007/978-3-319-91241-7_12

Cited by 61 publications

(46 citation statements)

References 24 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross-lingual and cross-cultural influences and similarities are important in linguistics (Shoemark et al, 2016;Levin et al, 1998;Sapir, 1921;Odlin, 1989;Cenoz, 2001;Toral and Way, 2018;De Raad et al, 1997;Hermans, 2003;Specia et al, 2016). The English word, "Beleaguer" originates from the Dutch word "belegeren"; "fidget" originates from the Nordic word "fikja".…”

Section: Language Families and Cross-lingual Learningmentioning

confidence: 99%

Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

Zhou¹,

Sperber²,

Waibel³

2018

Proceedings of the Third Conference on Machine Translation: Research Papers

View full text Add to dashboard Cite

We work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of lowresource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems. We build a translation system that addresses these challenges using eight European language families as our test ground. Firstly, we add the source and the target family labels and study intra-family and inter-family influences for effective cross-lingual transfer. We achieve an improvement of +9.9 in BLEU score for English-Swedish translation using eight families compared to the single-family multi-source multi-target baseline. Moreover, we find that training on two neighboring families closest to the low-resource language is often enough. Secondly, we construct an ablation study and find that reasonably good results can be achieved even with considerably less target data. Thirdly, we address the variable-binding problem by building an order-preserving named entity translation model. We obtain 60.6% accuracy in qualitative evaluation where our translations are akin to human translations in a preliminary study.

show abstract

Section: Language Families and Cross-lingual Learningmentioning

confidence: 99%

Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

Zhou¹,

Sperber²,

Waibel³

2018

Proceedings of the Third Conference on Machine Translation: Research Papers

View full text Add to dashboard Cite

show abstract

“…Voigt and Jurafsky [2] even state that literary MT may at first seem a "near-contradiction in terms", due to MT traditionally only being employed for informative texts. However, with the continuous advancements made in the field of neural machine translation (NMT), some researchers have tried to remove this stigma and provide more information on the applicability of NMT to literary texts [1,[3][4][5]. The aim of this article is to assess the performance of generic NMT systems on literary texts, by not only providing insights into the quality of the NMT, but by also examining more in-depth features such as lexical richness, local cohesion, syntactic and stylistic difference.…”

Section: Introductionmentioning

confidence: 99%

Gutenberg Goes Neural: Comparing Features of Dutch Human Translations with Raw Neural Machine Translation Outputs in a Corpus of English Literary Classics

et al. 2020

View full text Add to dashboard Cite

Due to the growing success of neural machine translation (NMT), many have started to question its applicability within the field of literary translation. In order to grasp the possibilities of NMT, we studied the output of the neural machine system of Google Translate (GNMT) and DeepL when applied to four classic novels translated from English into Dutch. The quality of the NMT systems is discussed by focusing on manual annotations, and we also employed various metrics in order to get an insight into lexical richness, local cohesion, syntactic, and stylistic difference. Firstly, we discovered that a large proportion of the translated sentences contained errors. We also observed a lower level of lexical richness and local cohesion in the NMTs compared to the human translations. In addition, NMTs are more likely to follow the syntactic structure of a source sentence, whereas human translations can differ. Lastly, the human translations deviate from the machine translations in style.

show abstract

“…Generating poetry through machines is not the same as translating it; it only seems more diicult and the point of coincidence is that a machine is used to deal with language in a highly creative and supposedly unexpected way. 1 As far as the translation of literary prose is concerned, there have been a few initiatives such as those reported on by Toral and Way (2018) and Toral, Wieling, and Way, (2018). In "What Level of Quality can Neural Machine Translation attain on Literary Text?"…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Another article by Toral and Way (Toral et al, 2018) gives a good overview of what has been achieved in the ield of machine translation and literary texts. In Toral and Way (2018) the authors analyse a chapter of a science iction novel translated by, irst, six professional translators and, second, by means of postedited PBMT and post-edited NMT. hey conclude that NMT, even more so than PBMT, helps when translating literature, at least in the case of novels, and that for professional translators the procedure is certainly faster than working purely from scratch.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tradução automática e poesia: o caso do inglês e do português

Humblé

2019

Ilha do Desterro

View full text Add to dashboard Cite

This article sets out to analyse the translations into Portuguese of three poems written I English, “A Letter is a Joy of Earth” by Emily Dickinson, “To a Stranger” by Walt Whitman and “Sandra” by Charles Bukowski. Three translations by three human translators, Geir Campos, Pedro Gonzaga and Jorge de Sena, are compared to the translations made by Google Translate in order to evaluate machine translation quality. This research shows that machine translations are less “ludicrous” than some would think and are in fact quite acceptable. In the cases investigated, machine translations are sometimes as acceptable as the ones made by the professional translators, and they could even help them to make mistakes through a lack of attention or by ignoring all the possibilities in the case of polysemous words. The Google translations are obviously plainer and there are a number of mistakes in them of the kind one expects: wrong concordances, wrong interpretations of polysemous words, wrong interpretation of gendered words. However, overall the results are far more satisfying than forecast. Google Translate, or similar programmes, may help translators with different, albeit sound alternatives. Additionally, machine translations provide a useful tool to analyse the idiosyncrasies of translators.

show abstract

What Level of Quality Can Neural Machine Translation Attain on Literary Text?

Cited by 61 publications

References 24 publications

Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

Gutenberg Goes Neural: Comparing Features of Dutch Human Translations with Raw Neural Machine Translation Outputs in a Corpus of English Literary Classics

Tradução automática e poesia: o caso do inglês e do português

Contact Info

Product

Resources

About