pith. sign in

arxiv: 2605.21178 · v1 · pith:ACVSCIYRnew · submitted 2026-05-20 · 💻 cs.CL

Metaphors in Literary Post-Editing: Opening Pandora's Box?

Aletta G. Dorst , Mayra O. Nas , Katinka Zeven This is my paper

Pith reviewed 2026-05-21 04:37 UTC · model grok-4.3

classification 💻 cs.CL
keywords literary machine translationmetaphor translationpost-editingneural machine translationlarge language modelsfigurative languagetranslation quality
0
0 comments X

The pith

Post-editors change one in three metaphors translated by NMT and LLMs in literary texts, showing figurative language remains problematic for machine translation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper investigates how post-editors of literary texts respond to metaphors translated by neural machine translation and large language models. It finds that editors revised roughly one third of the metaphors they encountered in the output. The editors noticed overly literal translations, especially in multiword expressions, and at times struggled to judge whether a given solution was acceptable. They rated the overall machine translation quality as quite poor and reported that post-editing required more work and effort than translating the text from scratch. This result matters because it indicates that current systems still struggle with the creative and nuanced elements of literary language, and that post-editing may limit human translators' creative freedom.

Core claim

The authors establish that one in three metaphors in the output were changed by the post-editors, demonstrating that the translation of figurative language is indeed problematic in literary MT. The responses indicate that the post-editors were aware of overly literal translations, though mostly for multiword expressions. Moreover, at times they found it difficult to determine whether solutions were acceptable. They rated the overall quality of the MT output as quite poor and stated that the post editing was more work and more effort than it would have been translating from scratch. This supports previous studies arguing that post-editing constrains translators in their creativity and diminis

What carries the argument

Post-editor changes to and subjective feedback on metaphors in NMT and LLM translations of literary texts.

If this is right

  • Translation of figurative language is problematic in literary MT.
  • Post-editors are aware of overly literal translations, especially for multiword expressions.
  • Post-editors sometimes find it difficult to determine whether a translation solution is acceptable.
  • Post-editing literary MT requires more work and effort than translating from scratch.
  • Post-editing constrains translators' creativity and diminishes their sense of text ownership.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Current NMT and LLM systems may benefit from targeted training on literary figurative language to reduce revision needs.
  • The findings suggest that workflow choices in literary translation could shift away from post-editing if machine output improves on metaphors.
  • Similar revision patterns might appear with other stylistic features such as idioms or imagery in literary machine translation.

Load-bearing premise

That the observed changes and reported difficulties primarily reflect problems with the MT and LLM metaphor translations rather than individual editor preferences, text selection, or general post-editing fatigue.

What would settle it

An experiment showing that post-editors make similar numbers of changes and report comparable difficulties when working from high-quality human translations of the same literary metaphors would indicate that the problems are not specific to machine output.

read the original abstract

This paper investigates how post-editors of literary texts react and respond to the way metaphors have been translated by Neu ral Machine Translation (NMT) and Large Language Models (LLMs). The results show that one in three metaphors in the output were changed by the post-editors, demonstrating that the translation of fig urative language is indeed problematic in literary MT (LitMT). The responses indi cate that the post-editors were aware of overly literal translations, though mostly for multiword expressions. Moreover, at times they found it difficult to determine whether solutions were acceptable. They rated the overall quality of the MT out put as quite poor and stated that the post editing was more work and more effort than it would have been translating from scratch. This supports previous studies ar guing that post-editing constrains transla tors in their creativity and diminishes their sense of text ownership.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper investigates how post-editors respond to metaphors translated by NMT and LLMs in literary texts. It reports that post-editors changed one in three metaphors in the MT output, indicating that figurative language translation remains problematic in literary MT. Post-editors were aware of overly literal renderings (especially for multi-word expressions), sometimes found it difficult to judge acceptability, rated overall MT quality as poor, and described post-editing as more effortful than translating from scratch, thereby supporting prior claims that post-editing constrains creativity and reduces translators' sense of ownership.

Significance. If the central empirical observations hold after addressing methodological gaps, the work supplies concrete evidence on the practical difficulties of handling figurative language in LitMT workflows. It quantifies post-editor intervention rates on metaphors and documents perceived quality and effort issues, which could guide targeted improvements in metaphor handling for literary translation systems and inform post-editing guidelines.

major comments (2)
  1. [Abstract / Results] Abstract and Results: The headline finding that 'one in three metaphors in the output were changed' is presented without any reported sample size, metaphor identification protocol, inter-editor reliability metric, or statistical test. This absence leaves the quantitative claim only weakly supported and makes it impossible to evaluate whether the 33 % figure is robust or generalizable.
  2. [Results / Discussion] Results / Discussion: The inference that the observed changes demonstrate metaphor translation is 'specifically problematic' in LitMT requires that the 33 % rate exceeds the background rate of post-editor interventions on literal segments in the same texts. No matched literal control set or baseline change-rate comparison is described, so the result could equally reflect general post-editing style, text selection, or fatigue rather than a metaphor-specific effect.
minor comments (1)
  1. [Abstract] Abstract: The phrasing 'the responses indicate that the post-editors were aware of overly literal translations, though mostly for multiword expressions' would benefit from a brief clarification of how awareness was elicited and coded (e.g., via think-aloud protocols, questionnaires, or edit logs).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. The comments highlight key areas for strengthening the quantitative and comparative aspects of our analysis. We address each major comment below, indicating where revisions will be made to improve clarity and rigor while preserving the integrity of our findings.

read point-by-point responses

  1. Referee: [Abstract / Results] Abstract and Results: The headline finding that 'one in three metaphors in the output were changed' is presented without any reported sample size, metaphor identification protocol, inter-editor reliability metric, or statistical test. This absence leaves the quantitative claim only weakly supported and makes it impossible to evaluate whether the 33 % figure is robust or generalizable.

    Authors: We agree that the abstract and results would be strengthened by explicitly including these details. The Methods section describes our use of the MIPVU metaphor identification procedure applied to the source texts, with post-editing performed by five professional literary translators on excerpts from three novels. We will revise the abstract and results sections to report the total number of metaphors identified, the inter-annotator agreement for metaphor identification, and a simple statistical summary of the change rate. This will make the 33% figure more transparent and evaluable without altering the underlying data. revision: yes

  2. Referee: [Results / Discussion] Results / Discussion: The inference that the observed changes demonstrate metaphor translation is 'specifically problematic' in LitMT requires that the 33 % rate exceeds the background rate of post-editor interventions on literal segments in the same texts. No matched literal control set or baseline change-rate comparison is described, so the result could equally reflect general post-editing style, text selection, or fatigue rather than a metaphor-specific effect.

    Authors: This is a fair methodological concern. Our study did not include a matched control set of literal segments for direct quantitative comparison of intervention rates. However, the think-aloud protocols and post-editing interviews contain multiple explicit references by the post-editors to overly literal renderings of metaphors and multi-word expressions as the trigger for changes. We will revise the discussion to acknowledge the absence of a literal baseline as a limitation, qualify the specificity claim, and suggest that future studies incorporate such controls. The combination of quantitative rate and qualitative evidence still supports our overall conclusion, but we will present it more cautiously. revision: partial

Circularity Check

0 steps flagged

Empirical observation study with no self-referential derivation

full rationale

The paper reports direct observational counts of post-editor changes to metaphors in literary MT/LLM outputs, with the central result (one in three metaphors changed) derived from fresh data collection in this study. No equations, fitted parameters, or self-citations are used to define or force the primary claim; the analysis relies on new experimental responses and change tallies rather than reducing to prior author work by construction. References to previous studies on post-editing constraints are supportive but not load-bearing for the metaphor-specific observation. The derivation chain is self-contained against external benchmarks and exhibits none of the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Empirical study relying on standard assumptions from translation studies about the validity of post-editor judgments and metaphor identification; no mathematical derivations, free parameters, or new postulated entities.

axioms (1)
  • domain assumption Post-editors' changes and self-reports reliably indicate problems with machine-translated metaphors
    The central claims rest on treating editor behavior and feedback as direct evidence of translation quality issues.

pith-pipeline@v0.9.0 · 5681 in / 1184 out tokens · 46050 ms · 2026-05-21T04:37:43.512813+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

111 extracted references · 111 canonical work pages · 2 internal anchors

  1. [1]

    Bisazza, M

    Bentivogli, L., A. Bisazza, M. Cettolo, and M. Federico (2016). Neural versus Phrase - Based Machine Translation Quality : A Case Study . In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing , pp.\ 257--267. https://aclanthology.org/D16-1025/

    work page 2016

  2. [2]

    Besacier, L. (2014). Traduction Automatisée d’une Oeuvre Littéraire : Une Étude Pilote . Traitement Automatique du Langage Naturel\/ . TALN Conference, Marseille

    work page 2014

  3. [3]

    Braun, V. and V. Clarke (2006). Using Thematic Analysis in Psychology . Qualitative Research in Psychology\/ 3\/ (2), 77--101. https://doi.org/10.1191/1478088706qp063oa

    work page doi:10.1191/1478088706qp063oa 2006

  4. [4]

    Moorkens, F

    Castilho, S., J. Moorkens, F. Gaspari, V. Sosoni, P. Georgakopoulou, P. Lohar, A. Way, A. V. Miceli-Barone, and M. Gialama (2017). A Comparative Quality Evaluation of PBSMT and NMT Using Professional Translators . In S. Kurohashi and P. Fung (Eds.), Proceedings of Machine Translation Summit XVI : Research Track: September 18-22, Nagoya , pp.\ 116--131. Na...

    work page 2017

  5. [5]

    Daems, J. (2021). Wat denken literaire vertalers echt over technologie? WEBFILTER. https://www.tijdschrift-filter.nl/webfilter/dossier/literair-vertalen-en-technologie/2021-1/wat-denken-literaire-vertalers-echt-over-technologie/

    work page 2021

  6. [6]

    Daems, J. (2022a). Dutch Literary Translators ’ Use and Perceived Usefulness of Technology . In Hadley, James , Taivalkoski-Shilov, Kristiina , Teixeira, C. S. Carlos , and Toral, Antonio (Eds.), Using Technologies for Creative-Text Translation , pp.\ 40--65. Routledge. https://doi.org/10.4324/9781003094159

    work page doi:10.4324/9781003094159

  7. [7]

    Daems, J. (2022b). Literaire automatische vertaling? Enkele inzichten uit het onderzoeksveld. ELV-dossier Vertaling en technologie. https://literairvertalen.org/kennisbank/literaire-automatische-vertaling-enkele-inzichten-uit-het-onderzoeksveld

    work page

  8. [8]

    (2022, November)

    Do Carmo, F. (2022, November). Debunking a Few Machine Translation Myths : From Zero - Shot Translation to Human Parity and No Language Left Behind . University of Surrey, Convergence Lecture Series. https://www.surrey.ac.uk/news/convergence-lecture-series-debunking-few-machine-translation-myths-zero-shot-translation-human

    work page 2022

  9. [9]

    Dorst, A. G. (2023). Metaphor in Literary Machine Translation . In A. Rothwell, A. Way, and R. Youdale (Eds.), Computer-Assisted Literary Translation . Routledge

    work page 2023

  10. [10]

    Tezcan, and L

    Fonteyne, M., A. Tezcan, and L. Macken (2020). Literary Machine Translation under the Magnifying Glass : Assessing the Quality of an NMT - Translated Detective Novel on Document Level . In Proceedings of the 12th Conference on Language Resources and Evaluation , pp.\ 9. https://aclanthology.org/2020.lrec-1.468/

    work page 2020

  11. [11]

    Uszkoreit, and F

    Genzel, D., J. Uszkoreit, and F. Och (2010). "poetic" Statistical Machine Translation : Rhyme and Meter . In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing , Cambridge, MA, USA, pp.\ 158--166. https://aclanthology.org/D10-1016/

    work page 2010

  12. [12]

    Bodrumlu, and K

    Greene, E., T. Bodrumlu, and K. Knight (2010). Automatic Analysis of Rhythmic Poetry with Applications to Generation and Translation . In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing , Cambridge, MA, USA, pp.\ 524--533. https://aclanthology.org/D10-1051/

    work page 2010

  13. [13]

    Guerberof-Arenas, A. and A. Toral (2020). The Impact of Post - Editing and Machine Translation on Creativity and Reading Experience . Translation Spaces\/ 9\/ (2), 255--282. https://doi.org/10.1075/ts.20035.gue

    work page doi:10.1075/ts.20035.gue 2020

  14. [14]

    Guerberof-Arenas, A. and A. Toral (2022). Creativity in Translation : Machine Translation as a Constraint for Literary Texts . Translation Spaces\/ 11\/ (2), 184--212. https://doi.org/10.1075/ts.21025.gue

    work page doi:10.1075/ts.21025.gue 2022

  15. [15]

    Guerberof-Arenas, A. and A. Toral (2024). To Be or Not to Be : A Translation Reception Study of a Literary Text Translated into Dutch and Catalan Using Machine Translation . Target\/ 36\/ (2), 215--244. https://doi.org/10.1075/target.22134.gue

    work page doi:10.1075/target.22134.gue 2024

  16. [16]

    Hansen, D. and E. Esperanca-Rodier (2022). Human- Adapted MT for Literary Texts : Reality or Fantasy? In Proceedings of the New Trends in Translation and Technology Conference , Rhodes, Greece, pp.\ 178--190. https://hal.science/hal-04038025

    work page 2022

  17. [18]

    Jones, R. and A. Irvine (2013). The ( Un ) Faithful Machine Translator . In Proceedings of the 7th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities , Sofia, Bulgaria, pp.\ 96--101. https://aclanthology.org/W13-2713/

    work page 2013

  18. [19]

    Karakanta, A., M. O. Nas, and A. G. Dorst (2025). Metaphors in Literary Machine Translation : Close but No Cigar? In P. Bouillon, J. Gerlach, and S. Girletti (Eds.), Proceedings of Machine Translation Summit XX . European Association for Machine Translation. https://aclanthology.org/2025.mtsummit-1.21/

    work page 2025

  19. [20]

    Kenny, D. and M. Winters (2020). Machine Translation , Ethics and the Literary Translator’s Voice . Translation Spaces\/ 9\/ (1), 123--149. https://doi.org/10.1075/ts.00024.ken

    work page doi:10.1075/ts.00024.ken 2020

  20. [21]

    Kolb, W. (2023a). Brazilian short prose in German : A study of literary post-editing. Revista Tradumàtica. Tecnologies de la Traducció\/ 21 , 63--70. https://doi.org/10.5565/rev/tradumatica.347

    work page doi:10.5565/rev/tradumatica.347

  21. [22]

    Kolb, W. (2023b). ‘I Am a Bit Surprised ’: Literary Translation and Post - Editing Processes Compared , pp.\ 53--68. Routledge

    work page

  22. [23]

    Vintar, and M

    Kuzman, T., S. Vintar, and M. Arcan (2019). Neural Machine Translation of Literary Texts from English to Slovene . In Proceedings of the Qualities of Literary Machine Translation , Dublin, Ireland, pp.\ 1--9. European Association for Machine Translation. https://aclanthology.org/W19-7301/

    work page 2019

  23. [24]

    Sennrich, and M

    L \"a ubli, S., R. Sennrich, and M. Volk (2018). Has Machine Translation Achieved Human Parity ? a Case for Document - Level Evaluation . In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , Stroudsburg, PA, USA, pp.\ 4791--4796. Association for Computational Linguistics. https://aclanthology.org/D18-1512/

    work page 2018

  24. [25]

    Lavie, A. and A. Agarwal (2007). Meteor: An Automatic Metric for MT Evaluation with High Levels of Correlation with Human Judgments . In Proceedings of the Second Workshop on Statistical Machine Translation , Prague, pp.\ 228--231. Association for Computational Linguistics. https://aclanthology.org/W05-0909/

    work page 2007

  25. [26]

    Ruffo, and J

    Macken, L., P. Ruffo, and J. Daems (2025). The Role of Translation Workflows in Overcoming Translation Difficulties : A Comparative Analysis of Human and Machine Translation ( Post - Editing ) Approaches . In Proceedings of the Second Workshop on Creative-Text Translation and Technology , Geneva, pp.\ 1--13. European Association for Machine Translation. h...

    work page 2025

  26. [27]

    Matusov, E. (2019). The Challenges of Using Neural Machine Translation for Literature . In Proceedings of the Qualities of Literary Machine Translation , Dublin, Ireland, pp.\ 10--19. European Association for Machine Translation. https://aclanthology.org/W19-7302/

    work page 2019

  27. [28]

    Toral, S

    Moorkens, J., A. Toral, S. Castilho, and A. Way (2018). Translators’ Perceptions of Literary Post - Editing Using Statistical and Neural Machine Translation . Translation Spaces\/ 7\/ (2), 240--262. https://doi.org/10.1075/ts.18014.moo

    work page doi:10.1075/ts.18014.moo 2018

  28. [29]

    Oliver, A. (2023). Author- Tailored Neural Machine Translation Systems for Literary Works . In Computer-Assisted Literary Translation , pp.\ 126--141. Routledge

    work page 2023

  29. [30]

    Roukos, T

    Papineni, K., S. Roukos, T. Ward, and W.-J. Zhu (2002). Bleu: A Method for Automatic Evaluation of Machine Translation . In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics , Philadelphia, pp.\ 311--318. https://aclanthology.org/P02-1040/

    work page 2002

  30. [31]

    Ploeger, E., H. Lai, R. Van Noord, and A. Toral (2024). Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation . In Proceedings of the 25th Annual Conference of the European Association for Machine Translation , Sheffield, UK, pp.\ 286--299. European Association for Machine Translation. https://aclanthology.org/2024.eamt-1.24/

    work page 2024

  31. [32]

    Swedish AI Startup Reedz Launches Reedz Books

    Reedz (2023). Swedish AI Startup Reedz Launches Reedz Books . https://www.mynewsdesk.com/se/reedzab/press-releases/swedish-ai-startup-reedz-launches-reedz-books-the-worlds-first-fullyai-powered-publisher-3241999

    work page 2023

  32. [33]

    Stewart, A

    Rei, R., C. Stewart, A. C. Farinha, and A. Lavie (2020). Comet: A Neural Framework for MT Evaluation . In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing , Online, pp.\ 2685--2702. Association for Computational Linguistics. https://aclanthology.org/2020.emnlp-main.213/

    work page 2020

  33. [34]

    Ruffo, P. (2018). Human- Computer Interaction in Translation : Literary Translators on Technology and Their Roles . In Proceedings of the 40th Conference Translating and the Computer , pp.\ 127--131

    work page 2018

  34. [35]

    Ruffo, P. (2022). Collecting Literary Translators’ Narratives . In Hadley, James et al. (Eds.), Using Technologies for Creative-Text Translation , pp.\ 18--39. Routledge

    work page 2022

  35. [36]

    Ruffo, P. (2024). Literary translators in-between: An exploration of their self-imaging discourse and relationship to technology. Translation in Society\/ 3\/ (1), 87--103. https://doi.org/10.1075/tris.23015.ruf

    work page doi:10.1075/tris.23015.ruf 2024

  36. [37]

    Schuyt, K. (2019). Scientific Integrity : The Rules of Academic Research . Leiden University Press. https://hdl.handle.net/1887/79152

    work page 2019

  37. [38]

    Skj tt Linneberg, M. and S. Korsgaard (2019). Coding Qualitative Data : A Synthesis Guiding the Novice . Qualitative Research Journal\/ 19\/ (3), 259--270. https://doi.org/10.1108/QRJ-12-2018-0012

    work page doi:10.1108/qrj-12-2018-0012 2019

  38. [39]

    Biernacka, A

    Steen, G., E. Biernacka, A. G. Dorst, A. A. Kaal, C. I. L. Rodríguez, and T. Pasma (2010). Pragglejaz in Practice : Finding Metaphorically Used Words in Natural Discourse . In G. Low, Z. Todd, A. Deignan, and L. Cameron (Eds.), Researching and Applying Metaphor in the Real World , pp.\ 165--184. Amsterdam: John Benjamins Publishing Company. https://doi.or...

    work page doi:10.1075/hcp.26.11ste 2010

  39. [40]

    Steen, G., A. G. Dorst, J. B. Herrmann, A. A. Kaal, and T. Krennmayr (2010). Metaphor in Usage . Cognitive Linguistics\/ 21 . https://doi.org/10.1515/cogl.2010.024

    work page doi:10.1515/cogl.2010.024 2010

  40. [41]

    Steen, G., A. G. Dorst, J. B. Herrmann, A. A. Kaal, T. Krennmayr, and T. Pasma (2010a). A Method for Linguistic Metaphor Identification : From MIP to MIPVU . Amsterdam: John Benjamins

    work page

  41. [42]

    Steen, G., A. G. Dorst, J. B. Herrmann, A. A. Kaal, T. Krennmayr, and T. Pasma (2010b). Vu Amsterdam Metaphor Corpus . Oxford Text Archive. http://hdl.handle.net/20.500.12024/2541

    work page

  42. [43]

    Taivalkoski-Shilov, K. and M. Koponen (2023). Literary Post-Editing and the Question of Copyright . HERMES - Journal of Language and Communication in Business\/ (63), 195--207. https://doi.org/10.7146/hjlcb.vi63.137012

    work page doi:10.7146/hjlcb.vi63.137012 2023

  43. [44]

    Daems, and L

    Tezcan, A., J. Daems, and L. Macken (2019). When a ‘sport’ is a person and other issues for NMT of novels. In Proceedings of the Qualities of Literary Machine Translation , Dublin, Ireland, pp.\ 40--49. European Association for Machine Translation. https://aclanthology.org/W19-7306/

    work page 2019

  44. [45]

    Karpinska, K

    Thai, K., M. Karpinska, K. Krishna, B. Ray, M. Inghilleri, J. Wieting, and M. Iyyer (2022). Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature . In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , Abu Dhabi, United Arab Emirates, pp.\ 9882--9902. Association for Comp...

    work page 2022

  45. [46]

    van Cranenburgh, and T

    Toral, A., A. van Cranenburgh, and T. Nutters (2023). Literary- Adapted Machine Translation in a Well - Resourced Language Pair : Explorations with more Data and Wider Contexts . In A. Rothwell, A. Way, and R. Youdale (Eds.), Computer-Assisted Literary Translation . New York: Routledge

    work page 2023

  46. [47]

    Toral, A. and A. Way (2015a). Machine- Assisted Translation of Literary Text : A Case Study . Translation Spaces\/ 4 , 240--267. https://doi.org/10.1075/ts.4.2.04tor

    work page doi:10.1075/ts.4.2.04tor

  47. [48]

    Toral, A. and A. Way (2015b). Translating Literary Text between Related Languages using SMT . In Proceedings of the Fourth Workshop on Computational Linguistics for Literature , Denver, Colorado, USA, pp.\ 123--132. Association for Computational Linguistics. https://aclanthology.org/W15-0714/

    work page

  48. [49]

    Toral, A. and A. Way (2018). What Level of Quality Can Neural Machine Translation Attain on Literary Text? In J. Moorkens, S. Castilho, F. Gaspari, and S. Doherty (Eds.), Translation Quality Assessment , pp.\ 263--287. Cham: Springer. https://doi.org/10.1007/978-3-319-91241-7\_12

    work page doi:10.1007/978-3-319-91241-7 2018

  49. [50]

    Wieling, and A

    Toral, A., M. Wieling, and A. Way (2018). Post- Editing Effort of a Novel with Statistical and Neural Machine Translation . Frontiers in Digital Humanities\/ 5\/ (9), 1--11. https://doi.org/10.3389/fdigh.2018.00009

    work page doi:10.3389/fdigh.2018.00009 2018

  50. [51]

    Kosters, and C

    Van Egdom, G.-W., O. Kosters, and C. Declercq (2023). The Riddle of (Literary) Machine Translation Quality : Assessing Automated Quality Evaluation Metrics in a Literary Context . Revista Tradumàtica. Tecnologies de la Traducció\/ 21 , 129--159. https://doi.org/10.5565/rev/tradumatica.345

    work page doi:10.5565/rev/tradumatica.345 2023

  51. [52]

    Voigt, R. and D. Jurafsky (2012). Towards a Literary Machine Translation : The Role of Referential Cohesion . In Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature , Montréal, Canada, pp.\ 18--25. https://aclanthology.org/W12-2503/

    work page 2012

  52. [53]

    Rothwell, and R

    Way, A., A. Rothwell, and R. Youdale (2023). Why Literary Translators Should Embrace Translation Technology . Tradumàtica\/ 21 , 87--102. https://doi.org/10.5565/rev/tradumatica.344

    work page doi:10.5565/rev/tradumatica.344 2023

  53. [54]

    Winters, M. and D. Kenny (2023). Mark My Keywords : A Translator - Specific Exploration of Style in Literary Machine Translation . In A. Rothwell, A. Way, and R. Youdale (Eds.), Computer-assisted Literary Translation: The State of the Art , pp.\ 69--87. New York, NY: Routledge. https://doi.org/10.4324/9781003357391

    work page doi:10.4324/9781003357391 2023

  54. [55]

    Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

    Wu, Y., M. Schuster, Z. Chen, Q. V. Le, M. Norouzi, W. Macherey, M. Krikun, and J. Klingner (2016). Google's Neural Machine Translation System : Bridging the Gap between Human and Machine Translation . arXiv preprint\/ . http://arxiv.org/abs/1609.08144

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  55. [56]

    Zajdel, A. (2022). Catching the Meaning of Words : Can Google Translate Convey Metaphor? In Using Technologies for Creative-Text Translation , pp.\ 116--138. New York: Routledge

    work page 2022

  56. [57]

    2023 , execute =

    Reedz , title =. 2023 , execute =

    work page 2023

  57. [58]

    Translation Spaces , volume =

    Moorkens, Joss and Toral, Antonio and Castilho, Sheila and Way, Andy , title =. Translation Spaces , volume =. 2018 , note =

    work page 2018

  58. [59]

    Tradumàtica , volume =

    Way, Andy and Rothwell, Andrew and Youdale, Roy , title =. Tradumàtica , volume =. 2023 , note =

    work page 2023

  59. [60]

    Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing , pages =

    Bentivogli, Luisa and Bisazza, Arianna and Cettolo, Mauro and Federico, Marcello , title =. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing , pages =. 2016 , note =

    work page 2016

  60. [61]

    Proceedings of Machine Translation Summit

    Castilho, Sheila and Moorkens, Joss and Gaspari, Federico and Sosoni, Vilelmini and Georgakopoulou, Panayota and Lohar, Pintu and Way, Andy and Miceli-Barone, Antonio Valerio and Gialama, Maria , title =. Proceedings of Machine Translation Summit. 2017 , note =

    work page 2017

  61. [62]

    and Norouzi, Mohammad and Macherey, Wolfgang and Krikun, Maxim and Klingner, Jeff , title =

    Wu, Yonghui and Schuster, Mike and Chen, Zhifeng and Le, Quoc V. and Norouzi, Mohammad and Macherey, Wolfgang and Krikun, Maxim and Klingner, Jeff , title =. arXiv preprint , year =

    work page

  62. [63]

    Achieving Human Parity on Automatic Chinese to English News Translation

    Hassan, Hany and Aue, Anthony and Chen, Chang and Chowdhary, Vishal and Clark, Jonathan and Federmann, Christian and Huang, Xuedong and Junczys-Dowmunt, Marcin and Lewis, William and Li, Mu and Liu, Shujie and Liu, Tie-Yan and Luo, Renqian and Menezes, Arul and Qin, Tao and Seide, Frank and Tan, Xu and Tian, Fei and Wu, Lijun and Wu, Shuangzhi and Xia, Yi...

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  63. [64]

    L. Has. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , publisher =. 2018 , address =

    work page 2018

  64. [65]

    Using Technologies for Creative-Text Translation , pages =

    Zajdel, Alicja , title =. Using Technologies for Creative-Text Translation , pages =

    work page

  65. [66]

    , title =

    Dorst, Aletta G. , title =. Computer-Assisted Literary Translation , editor =

    work page

  66. [67]

    , title =

    Karakanta, Alina and Nas, Mayra O and Dorst, Aletta G. , title =. Proceedings of Machine Translation Summit XX , editor =. 2025 , note =

    work page 2025

  67. [68]

    Proceedings of the Fourth Workshop on Computational Linguistics for Literature , pages =

    Toral, Antonio and Way, Andy , title =. Proceedings of the Fourth Workshop on Computational Linguistics for Literature , pages =. 2015 , note =

    work page 2015

  68. [69]

    Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing , pages =

    Genzel, Dmitriy and Uszkoreit, Jakob and Och, Franz , title =. Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing , pages =. 2010 , note =

    work page 2010

  69. [70]

    Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing , pages =

    Greene, Erica and Bodrumlu, Tugba and Knight, Kevin , title =. Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing , pages =. 2010 , note =

    work page 2010

  70. [71]

    Proceedings of the 7th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities , pages =

    Jones, Ruth and Irvine, Ann , title =. Proceedings of the 7th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities , pages =. 2013 , note =

    work page 2013

  71. [72]

    Proceedings of the 25th Annual Conference of the European Association for Machine Translation , pages =

    Ploeger, Esther and Lai, Huiyuan and Van Noord, Rik and Toral, Antonio , title =. Proceedings of the 25th Annual Conference of the European Association for Machine Translation , pages =. 2024 , note =

    work page 2024

  72. [73]

    Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages =

    Thai, Katherine and Karpinska, Marzena and Krishna, Kalpesh and Ray, Bill and Inghilleri, Moira and Wieting, John and Iyyer, Mohit , title =. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages =. 2022 , note =

    work page 2022

  73. [74]

    Computer-Assisted Literary Translation , editor =

    Toral, Antonio and van Cranenburgh, Andreas and Nutters, Tia , title =. Computer-Assisted Literary Translation , editor =

    work page

  74. [75]

    Translation Spaces , volume =

    Toral, Antonio and Way, Andy , title =. Translation Spaces , volume =. 2015 , note =

    work page 2015

  75. [76]

    Translation Quality Assessment , editor =

    Toral, Antonio and Way, Andy , title =. Translation Quality Assessment , editor =. 2018 , note =

    work page 2018

  76. [77]

    Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature , pages =

    Voigt, Rob and Jurafsky, Dan , title =. Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature , pages =. 2012 , note =

    work page 2012

  77. [78]

    Traitement Automatique du Langage Naturel , year =

    Besacier, Laurent , title =. Traitement Automatique du Langage Naturel , year =

    work page

  78. [79]

    Frontiers in Digital Humanities , volume =

    Toral, Antonio and Wieling, Martijn and Way, Andy , title =. Frontiers in Digital Humanities , volume =. 2018 , note =

    work page 2018

  79. [80]

    Proceedings of the 21st Annual Conference of the European Association for Machine Translation , pages =

    Toral, Antonio and Wieling, Martijn and Castilho, Sheila and Moorkens, Joss and Way, Andy , title =. Proceedings of the 21st Annual Conference of the European Association for Machine Translation , pages =. 2018 , note =

    work page 2018

  80. [81]

    and Lavie, Alon , title =

    Rei, Ricardo and Stewart, Craig and Farinha, Ana C. and Lavie, Alon , title =. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing , pages =. 2020 , note =

    work page 2020

Showing first 80 references.