English-to-Japanese Translation vs. Dictation vs. Post-editing: Comparing Translation Modes in a Multilingual Setting

English-to-Japanese Translation vs. Dictation vs. Post-editing: Comparing Translation Modes in a Multilingual Setting Michael Carl1,2, Akiko Aizawa2,3 and Masaru Yamada4 1CRITT, Copenhagen Business School, Copenhagen, Denmark 2NII, National Institute of Informatics, Tokyo, Japan 3Tokyo University, Tokyo, Japan 4Kansai University, Osaka, Japan E-mail: mc.ibc@cbs.dk, aizawa@nii.ac.jp, yamada@apple-eye.com Abstract Speech-enabled interfaces have the potential to become one of the most efficient and ergonomic environments for human-computer interaction and for text production. However, not much research has been carried out to investigate in detail the processes and strategies involved in the different modes of text production. This paper introduces and evaluates a corpus of more than 55 hours of English-to-Japanese user activity data that were collected within the ENJA15 project, in which translators were observed while writing and speaking translations (translation dictation) and during machine translation post-editing. The transcription of the spoken data, keyboard logging and eye-tracking data were recorded with Translog-II, post-processed and integrated into the CRITT TPR-DB1, which is publicly available under a creative commons license. The paper presents the ENJA15 data as part of a large multilingual Chinese, Danish, German, Hindi and Spanish translation process data collection of more than 760 translation sessions. It compares the ENJA15 data with the other language pairs and reviews some of its particularities. Keywords: translation dictation, translation process research, multi-lingual translation corpora 1. Introduction Translation dictation is a mode of translation by which a translator reads a source text and speaks out its translation in the target language, rather than typing it. Translation dictation is thus a method of translation situated in between interpretation, where the interpreter hears a text and speaks out the translation (e.g., during conference interpreting) and conventional translation by which a written source text is translated mainly using the keyboard. It is close to sight translation, but while sight translation is usually done in the moment; there are – in principle - no time constraints in translation dictation. Translation dictation was used in some translation bureaus in the 1960s and 1970s (Gingold, 1978) but it has been used less frequently since the mid-80s, as professional translators started using micro-computers (Zapata and Kirkedal, 2015). Already the ALPAC report (Pierce et al., 1966) mentioned that “productivity of human translators might be as much as four times higher when dictating” as compared to writing. Others (e.g. Reddy and Rose, 2010, Rodriguez et al., 2012) are less optimistic about the time efficiency of dictation, but with increasing quality of voice recognition this mode of translation is becoming a valid alternative to ‘conventional’ translation typing (Ciobanu, 2014) and even to machine translation post-editing. See also Martinez et al, (2014) who experiment with integrating speech recognition into an online CAT system. While translation dictation in the 1960s and 1970s was spoken on tape and transcribed by a (monolingual) typist, the usage of Automatic Speech Recognition (ASR) systems provides today an efficient means to produce texts directly without the need for an extra typist. Our experiments suggest that for some translators and types of texts it might become …

Content truncated to 500 words