CATaLog Online: Porting a Post-editing Tool to the Web

CATaLog Online: Porting a Post-editing Tool to the Web Santanu Pal1, Marcos Zampieri1,2, Sudip Kumar Naskar3, Tapas Nayak3, Mihaela Vela1, Josef van Genabith1,2 Saarland University, Germany1, German Research Center for Artificial Intelligence (DFKI), Germany2 Jadavpur University, India3 {santanu.pal, marcos.zampieri, josef.vangenabith}@uni-saarland.de, m.vela@mx.uni-saarland.de, tnk02.05@gmail.com, sudip.naskar@cse.jdvu.ac.in Abstract This paper presents CATaLog online, a new web-based MT and TM post-editing tool. CATaLog online is a freeware software that can be used through a web browser and it requires only a simple registration. The tool features a number of editing and log functions similar to the desktop version of CATaLog enhanced with several new features that we describe in detail in this paper. CATaLog online is designed to allow users to post-edit both translation memory segments as well as machine translation output. The tool provides a complete set of log information currently not available in most commercial CAT tools. Log information can be used both for project management purposes as well as for the study of the translation process and translator’s productivity. Keywords: post-editing, machine translation, translation memories 1. Introduction With the improvement of machine translation (MT) soft- ware, post-editing tools have become an important part of the translation workflow. In recent years, commercial computer-aided translation (CAT) tools have started to pro- vide not only the popular translation memory (TM) matches but also MT segments to be post-edited by translators. The use of MT output for post-editing is regarded to increase translator’s productivity and also to improve consistency in translation (Federico et al., 2012; Zampieri and Vela, 2014). In light of this, a recent trend in the field is to develop tools that integrate both MT and TM output providing translators a larger number of more useful and more accurate sugges- tions (Cettolo et al., 2013). Contributing in this direction, this paper presents a new web-based CAT tool called CATaLog online1 developed based on CATaLog, a recently-released desktop CAT tool (Nayek et al., 2015). The tool can be used to post-edit MT output as well as TM segments. CATaLog online records a wide range of logs that are not available in any commer- cial CAT tool making it a useful tool for project manage- ment and translation process research. We have observed a substantial increase in the number of online CAT tools available, both for commercial and non-commercial pur- poses. This includes tools such as WordFast Anywhere2, MateCat3 (Federico et al., 2014), Wordbee4, and many oth- ers. In our opinion, this is a trend in the translation in- dustry and it motivated us to release CATaLog online. On- line CAT tools have a number of advantages over desktop tools, most notably: they do not require local installation; they can be used from any computer; projects can be eas- ily shared with multiple translators; project managers can track the progress of projects on the fly. This paper presents CATaLog online and summarizes the 1The tool is available online. For more information, consult the following URL: http://ttg.uni-saarland.de/software/catalog 2https://www.freetm.com/ 3http://www.matecat.com 4http://www.wordbee.com/ new features implemented in this tool as …

Content truncated to 500 words