Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 1, 2025Yearbook of PhraseologyOpen Access

Measuring Creative Phraseology in Literature: Machine Translation Systems Versus Large Language Models

View Full Paper
Ask AI
Bookmark
Share

Authors

LSLaura Noriega SantiáñezGPGloria Corpas Pastor

Discussion

Loading...

Member takes

Overview

This analysis finds neural machine translation systems outperform human translation in morphosyntactic aspects, indicating potential for literary applications.

Key Points

  • The aim is to assess the output quality of machine translation systems and large language models in literary translation.
  • Evaluated five comparative idioms from literary texts in English to Spanish.
  • Compared outputs of neural machine translation systems like DeepL and Google Translate with those of LLMs like ChatGPT and Gemini.
  • Assessed outputs against human translations using creativity measurement parameters.
  • Human translation (HT) excelled overall in quality assessment.
  • NMT systems outperformed HT morphosyntactically.
  • LLMs, particularly ChatGPT, showed promising results in creativity.

Cite This Study

Santiáñez et al. (2025) studied this question.

synapsesocial.com/papers/6925435ec0ce034ddc35806dhttps://doi.org/10.1515/phras-2025-0006
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Human versus Neural Machine Translation Creativity: A Study on Manipulated MWEs in Literature2024 · 2 citations
  2. 2Exploring AI’s performance in literary autobiography translation: how closely do AI models match human translation2026 · 4 citations
  3. 3Assessing the Quality of Large Language Models in Machine Translation Tasks2026
  4. 4Evaluating the limits of machine translation for poetry: a multidimensional framework2026
  5. 5In search of a translator: using AI to evaluate what's lost in translation2024 · 12 citations