Multi-Engine Machine Translation by Recursive Sentence Decomposition
نویسندگان
چکیده
In this paper, we present a novel approach to combine the outputs of multiple MT engines into a consensus translation. In contrast to previous Multi-Engine Machine Translation (MEMT) techniques, we do not rely on word alignments of output hypotheses, but prepare the input sentence for multi-engine processing. We do this by using a recursive decomposition algorithm that produces simple chunks as input to the MT engines. A consensus translation is produced by combining the best chunk translations, selected through majority voting, a trigram language model score and a confidence score assigned to each MT engine. We report statistically significant relative improvements of up to 9% BLEU score in experiments (English→Spanish) carried out on an 800sentence test set extracted from the PennII Treebank.
منابع مشابه
A Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کاملApplying Referenceless MT Evaluation Metrics to a Multi-Engine MT System
Recent work in the area of automatic machine translation evaluation has led to the development of metrics that have equivalent levels of performance with standard metrics, yet do not rely on the existence of human generated gold standard reference translations. To achieve this performance, alternative machine generated translation are used in place of the human references. A seemingly natural a...
متن کاملSearch Engine Guided Non-Parametric Neural Machine Translation
In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first stage–retrieval stage–, an off-the-shelf, black-box search engine is used to retrieve a small subset of sentence pairs from a training set given a source sente...
متن کاملOn the Properties of Neural Machine Translation: Encoder-Decoder Approaches
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on a...
متن کاملHybrid System Combination for Machine Translation: An Integration of Phrase-level and Sentence-level Combination Approaches
Hybrid System Combination for Machine Translation: An Integration of Phrase-level and Sentence-level Combination Approaches Wei-Yun Ma Given the wide range of successful statistical MT approaches that have emerged recently, it would be beneficial to take advantage of their individual strengths and avoid their individual weaknesses. Multi-Engine Machine Translation (MEMT) attempts to do so by ei...
متن کامل