Statistical Machine Translation
Cambridge University Press, 2010 - 433 頁
La 4e de couverture indique : "The field of machine translation has recently been energized by the emergence of statistical techniques, which have brought the dream of automatic language translation closer to reality. This class-tested textbook, authored by an active researcher in the field, provides a gentle and accessible introduction to the latest methods and enables the reader to build machine translation systems for any language pair. It provides the necessary grounding in linguistics and probabilities, and covers the major models for machine translation: word-based, phrase-based, and tree-based, as well as machine translation evaluation, language modeling, discriminative training, and advanced methods to integrate linguistic annotation. The book reports on the latest research and outstanding challenges, and enables novices as well as experienced researchers to make contributions to the field. It is ideal for students at undergraduate and graduate level, or for any reader interested in the latest developments in machine translation."
讀者評論 - 撰寫評論
algorithm alignment points Annual Meeting ofthe Association for Computational back-off best translation bigrams BLEU score candidate translations Chapter chart entries Computational Linguistics conﬁdence counts decoding deﬁne efﬁcient English words Europarl Europarl corpus example extracted Figure ﬁnd ﬁnite ﬁrst foreign word function words grammar rules Haus human translators hypothesis IBM Model input sentence input words instance IWSLT Koehn language model lexical translation log-linear model machine learning machine translation systems mapping match Meeting ofthe Association methods morphological n-best list n-gram Natural Language Processing node nonterminal order n-gram output words parallel corpora parallel corpus parameter parse parse tree part-of-speech tags phrase pairs phrase-based models possible probability distribution problem Proceedings ofthe pruning reference translation reordering model sentence pair sequence span speciﬁc Spoken Language Translation stack statistical machine translation structure tion training data translation options translation probability transliteration tree verb word alignment word error rate Workshop on Spoken Workshop on Statistical