In this paper, we demonstrate that accurate machine translation is possible without the concept of “words,” treating MT as a problem of transformation between character string...
Graham Neubig, Taro Watanabe, Shinsuke Mori, Tatsu...
Many machine translation (MT) evaluation metrics have been shown to correlate better with human judgment than BLEU. In principle, tuning on these metrics should yield better syste...
For resource-limited language pairs, coverage of the test set by the parallel corpus is an important factor that affects translation quality in two respects: 1) out of vocabulary ...
Abstract. We present a systematic comparison of preprocessing techniques for two language pairs: English-Czech and English-Hindi. The two target languages, although both belonging ...
Machine translation of human languages is a field almost as old as computers themselves. Recent approaches to this challenging problem aim at learning translation knowledge automat...
We show here the viability of a rapid deployment of a new language pair within the METIS architecture. Contrarily to other SMT or EBMT systems, the METIS architecture allows us to...
In this paper, we describe our work on building a parallel treebank for a less studied and typologically dissimilar language pair, namely Swedish and Turkish. The treebank is a ba...
The performance of machine translation systems varies greatly depending on the source and target languages involved. Determining the contribution of different characteristics of l...
Most cross language information retrieval research concentrates on language pairs for which direct, rich, and often multiple translation resources already exist. However, for most...
In this paper, we present an empirical study that utilizes morph-syntactical information to improve translation quality. With three kinds of language pairs matched according to mor...