You Are What You Read

Category: Machine Translation

  • Stop the tuning on Tanzil

      Recently, I’ve been practising tuning on Tanzil data set using MOSES. My data set is from Ja-Id and vice versa. When I’m doing from Id-Ja, it takes a long time: more than 1 days! Actually, tuning process can be done in days. But, if you want to stop and see the weight between the…

  • MOSES tuning

    When you run tuning in MOSES, for example you running this script: nohup nice ~/mosesdecoder/scripts/training/mert-moses.pl \ ~/corpus/news-test2008.true.fr ~/corpus/news-test2008.true.en \ ~/mosesdecoder/bin/moses train/model/moses.ini –mertdir ~/mosesdecoder/bin/ \ &> mert.out & then you want to know the output of mert.out, you can use this command in another terminal: tail -f mert.out The tuning process will be shown in second…

  • Installing MOSES

    Hi! In this article, we will installing MOSES and running it for the first time. What do you need? Well, I use Ubuntu for operating system. After you install Ubuntu, you need to follow the instruction in this site. But I will simplify the instruction. So, what we need for the first time are: Ubuntu…

  • Machine Translation Approach

        Translasi Mesin (Machine Translation/MT) adalah sebuah metode untuk melakukan penterjemahan dari sumber bahasa yang satu ke bahasa yang lain. Beberapa pendekatan untuk melakukan translasi adalah: Rule-Based Rule-Based MT (RBMT) dikenal juga dengan nama Knowledge-Based MT dan Classical-Approach MT. Seperti namanya, pendekatan ini didasarkan pada aturan-aturan seperti tata-bahasa (grammar) yang meliputi semantic, morphologi, dan…

  • Web Crawling for Sunda WordNet

    One of my research is in Sunda WordNet. I have been dividing this research with two students: Muh. Ikhlas Wicaksono, will be doing web crawling for looking Sundanese word in Sundanese and Indonesian Wikipedia. Extract and store it in the database. Billy Al Gifary, will be doing words extraction from Sundanese dictionary and store it in…

  • Terms in Machine Translation

    Some terms in Machine Translation are: Lexicons is dictionaries which have to be change in online or digital Words Lemma Corpus Senses