Translation Quality Indicators for Pivot-based Statistical MT
نویسندگان
چکیده
Recent research on multilingual statistical machine translation focuses on the usage of pivot languages in order to overcome resource limitations for certain language pairs. This paper provides new insights into what factors make a good pivot language and investigates the impact of these factors on the overall pivot translation performance. Pivot-based SMT experiments translating between 22 IndoEuropean and Asian languages were used to analyze the impact of eight factors (language family, vocabulary, sentence length, language perplexity, translation model entropy, reordering, monotonicity, engine performance) on pivot translation performance. The results showed that 81% of system performance variations can be explained by these factors.
منابع مشابه
Employing Pivot Language Technique through Statistical and Neural Machine Translation Frameworks: the Case of Under-resourced Persian-spanish Language Pair
The quality of Neural Machine Translation (NMT) systems like Statistical Machine Translation (SMT) systems, heavily depends on the size of training data set, while for some pairs of languages, high-quality parallel data are poor resources. In order to respond to this low-resourced training data bottleneck reality, we employ the pivoting approach in both neural MT and statistical MT frameworks. ...
متن کاملMulti-pivot translation by system combination
This paper describes a technique to exploit multiple pivot languages when using machine translation (MT) on language pairs with scarce bilingual resources, or where no translation system for a language pair is available. The principal idea is to generate intermediate translations in several pivot languages, translate them separately into the target language, and generate a consensus translation...
متن کاملTriangulation of Reordering Tables: An Advancement Over Phrase Table Triangulation in Pivot-Based SMT
Triangulation in Pivot-Based Statistical Machine Translation(SMT) is a very effective method for building Machine Translation(MT) systems in case of scarcity of the parallel corpus. Phrase Table Triangulation helps in such a resource constrained setting by inducing new phrase pairs with the help of a pivot. However, it does not explore the possibility of extracting reordering information throug...
متن کاملPivot-based Machine Translation between Statistical and Black Box systems
This paper presents a novel approach to pivot-based machine translation (MT): while the state-of-the-art uses two statistical systems, this proposal treats the second system as a black box. Our approach effecively provides pivot-based MT to target languages for which no suitable bilingual corpora are available to build statistical systems, as long as any other kind of MT system is available. We...
متن کاملThe TCH machine translation system for IWSLT 2008
This paper reports on the first participation of TCH (Toshiba (China) Research and Development Center) at the IWSLT evaluation campaign. We participated in all the 5 translation tasks with Chinese as source language or target language. For Chinese-English and English-Chinese translation, we used hybrid systems that combine rule-based machine translation (RBMT) method and statistical machine tra...
متن کامل