Post-editing Effort of a Novel With Statistical and Neural Machine Translation
Authors:
Top Cited Papers
Open Access
- 15 May 2018
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Digital Humanities
- Vol. 5
Abstract
We conduct the first experiment in the literature in which a novel is translated automatically and then post-edited by professional literary translators. Our case study is Warbreaker, a popular fantasy novel originally written in English, which we translate into Catalan. We translated one chapter of the novel (over 3,700 words, 330 sentences) with two data-driven approaches to Machine Translation (MT): phrase-based statistical MT (PBMT) and neural MT (NMT). Both systems are tailored to novels; they are trained on over 100 million words of fiction. In the post-editing experiment, six professional translators with previous experience in literary translation translate subsets of this chapter under three alternating conditions: from scratch (the norm in the novel translation industry), post-editing PBMT, and post-editing NMT. We record all the keystrokes, the time taken to translate each sentence, as well as the number of pauses and their duration. Based on these measurements, and using mixed-effects models, we study post-editing effort across its three commonly studied dimensions: temporal, technical and cognitive. We observe that both MT approaches result in increases in translation productivity: PBMT by 18%, and NMT by 36%. Post-editing also leads to reductions in the number of keystrokes: by 9% with PBMT, and by 23% with NMT. Finally, regarding cognitive effort, post-editing results in fewer (29 and 42% less with PBMT and NMT, respectively) but longer pauses (14 and 25%).Keywords
This publication has 16 references indexed in Scilit:
- Neural Machine Translation of Rare Words with Subword Units2016
- Translating Literary Text between Related Languages using SMT2015
- AUTOMATED TRANSLATION OF A LITERARY WORK: A PILOT STUDY2015
- The effects of direct and indirect speech on discourse comprehension in Dutch listeners with and without aphasiaAphasiology, 2014
- The efficacy of human post-editing for language translation2013
- Analyzing Linguistic Data2012
- Quantitative Social Dialectology: Explaining Linguistic Variation Geographically and SociallyPLOS ONE, 2011
- A Productivity Test of Statistical Machine Translation Post-Editing in a Typical Localisation ContextThe Prague Bulletin of Mathematical Linguistics, 2010
- Pauses as Indicators of Cognitive Effort in Post-editing Machine Translation OutputAcross Languages and Cultures, 2006
- NLTK2006