Sensible: L2 Translation Assistance by Emulating the Manual Post-Editing Process
نویسندگان
چکیده
This paper describes the Post-Editor Z system submitted to the L2 writing assistant task in SemEval-2014. The aim of task is to build a translation assistance system to translate untranslated sentence fragments. This is not unlike the task of post-editing where human translators improve machine-generated translations. Post-Editor Z emulates the manual process of post-editing by (i) crawling and extracting parallel sentences that contain the untranslated fragments from a Web-based translation memory, (ii) extracting the possible translations of the fragments indexed by the translation memory and (iii) applying simple cosine-based sentence similarity to rank possible translations for the untranslated fragment.
منابع مشابه
Translation Quality and Effort: Options versus Post-editing
Past research has shown that various types of computer assistance can reduce translation effort and improve translation quality over manual translation. This paper directly compares two common assistance types – selection from lists of translation options, and postediting of machine translation (MT) output produced by Google Translate – across two significantly different subject domains for Chi...
متن کاملThe Effects of Collaborative and Individual Output Tasks on Learning English Collocations
One of the most problematic areas in foreign language learning is collocation. It is often seen as arbitrary and an overwhelming obstacle to the achievement of nativelike fluency. Current second language (L2) instruction research has encouraged the use of collaborative output tasks in L2 classrooms. This study examined the effects of two types of output tasks (editing and cloze) on the learni...
متن کاملPerception vs Reality: Measuring Machine Translation Post-Editing Productivity
This paper presents a study of user-perceived vs real machine translation (MT) post-editing effort and productivity gains, focusing on two bidirectional language pairs: English— German and English—Dutch. Twenty experienced media professionals post-edited statistical MT output and also manually translated comparative texts within a production environment. The paper compares the actual post-editi...
متن کاملPerception vs Reality: Measuring Machine Translation Post-Editing Productivity
This paper presents a study of user-perceived vs real machine translation (MT) post-editing effort and productivity gains, focusing on two bidirectional language pairs: English— German and English—Dutch. Twenty experienced media professionals post-edited statistical MT output and also manually translated comparative texts within a production environment. The paper compares the actual post-editi...
متن کاملStatistical Machine Translation for Automobile Marketing Texts
We describe a project on introducing an in-house statistical machine translation system for marketing texts from the automobile industry with the final aim of replacing manual translation with post-editing, based on the translation system. The focus of the paper is the suitability of such texts for SMT; we present experiments in domain adaptation and decompounding that improve the baseline tran...
متن کامل