Data Issues of the Multilingual Translation Matrix
نویسنده
چکیده
We describe our experiments with phrasebased machine translation for the WMT 2012 Shared Task. We trained one system for 14 translation directions between English or Czech on one side and English, Czech, German, Spanish or French on the other side. We describe a set of results with different training data sizes and subsets.
منابع مشابه
Transculturation and Multilingual Lives: Writing between Languages and Cultures
This paper looks at the issues of transculturation as explored in auto and semi-autobiographical accounts of linguistic and cultural transitions. The paper also addresses a number of questions about the structure of these texts, the authors’ linguistic competences, as well as questions about the theoretical and conceptual tool which may help us to discuss the issues the writers are reflecting o...
متن کاملTranslation Quality Assessment of English Equivalents of Persian Proper Nouns: A case of bilingual tourist signposts in Isfahan
Abstract This study evaluated the translation quality of English equivalents of Persian proper nouns in the tourist signs and bilingual boards in Isfahan. To find different errors in the translations of the bilingual boards and tourist signs, the data were collected directly by taking picture or writing exactly from the available tourist signs and bilingual boards. Then, the errors were assesse...
متن کاملTranslation Quality Assessment of English Equivalents of Persian Proper Nouns: A case of bilingual tourist signposts in Isfahan
Abstract This study evaluated the translation quality of English equivalents of Persian proper nouns in the tourist signs and bilingual boards in Isfahan. To find different errors in the translations of the bilingual boards and tourist signs, the data were collected directly by taking picture or writing exactly from the available tourist signs and bilingual boards. Then, the errors were assesse...
متن کاملNeural Machine Translation for Low Resource Languages using Bilingual Lexicon Induced by Comparable Corpora
Automatically extracting parallel sentence pairs from the multilingual articles available on the Internet can address the data sparsity problem in building multilingual natural language processing applications, especially in machine translation. In this project, we have used an end-to-end siamese bidirectional recurrent neural network to generate parallel sentences from comparable multilingual ...
متن کاملCommunicative Strategies and Patterns of Multimodal Integration in a Speech-to-Speech Translation System
When multilingual communication through a speech-to-speech translation system is supported by multimodal features, e.g. pen-based gestures, the following issues arise concerning the nature of the supported communication: a) to what extend does multilingual communication differ from ‘ordinary’ monolingual communication with respect to the dialogue structure and the communicative strategies used ...
متن کامل