Browsing Data Science Institute by Author "Popovic, Maja"

Now showing items 1-6 of 6

    • Asistent -- a machine translation system for Slovene, Serbian and Croatian 

      Arcan, Mihael; Popovic, Maja; Buitelaar, Paul (University of Ljubljana, 2016-09-29)
      The META-NET research on language technologies in 2012 showed a weak support on tools for crossing the language barrier for many European languages, including the south Slavic languages. Therefore, we describe a statistical ...

    • Identifying main obstacles for statistical machine translation of morphologically rich South Slavic languages 

      Popovic, Maja; Arcan, Mihael (European Association for Machine Translation, 2015-05-11)
      The best way to improve a statistical machine translation system is to identify concrete problems causing translation errors and address them. Many of these problems are related to the characteristics of the involved ...

    • Language related issues for machine translation between closely related south Slavic languages 

      Popovic, Maja; Arcan, Mihael; Klubicka, Filip (The COLING 2016 Organizing Committee, 2016-12-12)
      Machine translation between closely related languages is less challenging and exhibits a smaller number of translation errors than translation between distant languages, but there are still obstacles which should be ...

    • PE2 rr corpus: manual error annotation of automatically pre-annotated MT post-edits 

      Popovic, Maja; Arcan, Mihael (European Language Resources Association, 2016-05-23)
      We present a freely available corpus containing source language texts from different domains along with their automatically generated translations into several distinct morphologically rich languages, their post-edited ...

    • Poor man’s lemmatisation for automatic error classification 

      Popovic, Maja; Arcan, Mihael; Avramidis, Eleftherios; Burchardt, Aljoscha; Lommel, Arle (European Association for Machine Translation, 2015-04-11)
      This paper demonstrates the possibility to make an existing automatic error classifier for machine translations independent from the requirement of lemmatisation. This makes it usable also for smaller and under-resourced ...

    • Potential and limits of using post-edits as reference translations for MT evaluation 

      Popovic, Maja; Arcan, Mihael; Lommel, Arle (Vilnius University, University of Latvia, Latvia University of Agriculture, Institute of Mathematics and Informatics of University of Latvia, 2016-05-30)
      This work investigates the potential use of post-edited machine translation (MT) outputs as reference translations for automatic machine translation evaluation, focusing mainly on the following important question: Is it ...