Correlating process and product data to get an insight into translation difficulty
Bibliographic Data
| ID | 12183291 |
|---|---|
| Authors | Bram Vanroy (0000-0002-4622-8364, LT3, Language and Translation Technology Team, Ghent University, Ghent, Belgium, corresponding author), Orphée De Clercq (0000-0002-6090-5552, LT3, Language and Translation Technology Team, Ghent University, Ghent, Belgium), Lieve Macken (0000-0001-7516-7487, LT3, Language and Translation Technology Team, Ghent University, Ghent, Belgium) |
| Year | 2019 |
| Volume | 27 |
| Issue | 6 |
| Pages | 924-941 |
| Publication date | 2019-03-29 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Perspectives (JOURNAL) |
| Journal identifiers | ISSN: 0907-676X • E-ISSN: 1747-6623 |
| Publisher | Taylor & Francis (PUBLISHER • GB) |
| DOI | 10.1080/0907676x.2019.1594319 |
| OpenAlex | W2926605700 |
| Language | EN |
| Citations received | 6 |
| References cited | 17 |
Research in the field of translation studies suggests that translation product features can indicate translation difficulty. In the current pilot study, we investigate three of these features, namely the number of errors made in a translation, word translation entropy and degree of syntactic equivalence. We correlate these translation product features with translation process features that can be put together into three categories: duration, revision and gaze information. These features serve as a proxy for the cognitive effort required to solve difficulties in translation. The data that we used was gathered from professional translators as well as students of translation studies. The product data contains manual error annotations of the translations, automatically calculated entropy values and syntactic re-ordering metrics. The process data are derived from keystroke and eye-tracking data gathered during the translation process. By correlating product and process data, we inspect how translation difficulty is reflected in the translation process and whether it is feasible to use product features to predict difficulties in translation. In addition, we also compare data of professional translators and students. We will show that correlations between process and product features exist, which opens many doors to further research on translatability
Dynamic and formal equivalence · Equivalence (formal languages · Keystroke logging · Linguistics · Machine translation · Natural language processing · Process (computing · Product (mathematics · Translation (biology · Computer Science · Mathematics · Natural Language Processing Techniques · Text Readability and Simplification · Translation Studies and Practices · Artificial Intelligence
Methodology of Cognitive-Discursive Modelling of Literary Translation (Case Study of Ukrainian Retranslations of W. Shakespeare’s Tragedies of the 19th–21st Centuries)
Adequacy, fluency and cognitive processes
The impact of an industry-driven translation training program on the performance of trainee translators
An analysis of pause placement in bursts of writing in translation
Effect of dependency distance of source text on disfluencies in interpreting
Effect of text type on translation effort in human translation and neural machine translation post-editing processes
In Other Words
Keystroke Logging in Writing Research
Computational assessment of text readability
Pauses as Indicators of Cognitive Effort in Post-editing Machine Translation Output
Measuring translation difficulty
All Mixed Up ? Finding the Optimal Feature Set for General Readability Prediction and Its Application to English and Dutch
Gazing and Typing Activities during Translation
Translation Methods and Experience
| Citations per year | 1 |
|---|---|
| Citation span | 2020 - 2026 (7) |
| Highly cited | No |