Báo cáo khoa học: "Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora" pptx

... Linguistics Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora Trevor Cohn and Mirella Lapata Human Computer Research Centre, School of Informatics University of Edinburgh {tcohn,mlap}@inf.ed.ac.uk Abstract Current ... corpora because the translation algorithm must rely on more sparse estimates of phrase fre- quencies and must also ‘ba...

Ngày tải lên: 31/03/2014, 01:20

... measured by the average number of hyperedges (h = 1 for CF). “lattice” is the average number of edges in the original CN. of hyperedges 3 . The larger potentials do not imply better translations, ... Christof Monz, Kay Peterson, Mark Przybocki, and Omar Zaidan. 2010. Findings of the 2010 joint workshop on sta- tistical machine translation and metrics for machine translation. In P...

Ngày tải lên: 07/03/2014, 22:20

... subtree are used as penalty terms. y Entropy: the entropy of the word to word translation probability of the English word i e . y Part -of- Speech mapping template: whether the POS tags of the ... modeled translation as a sequence of tree operations transforming a syntactic tree into a string of the target language. When researchers try to use syntax trees in both lan...

Ngày tải lên: 20/02/2014, 15:20

Ngày tải lên: 21/02/2014, 20:20

... a set of target language terms, to decide on correct use of prepositions, or any com- bination of the-~e and other similar tasks. Shifting towards the end of the scale where the bulk of the ... regular operational use or under development, will reveal a wide range of different types of systems. If we take first the dimension determined by who/what does most of th...

Ngày tải lên: 21/02/2014, 20:20

... has of what a translation should be. Translation can only be defined in particular situations, regarding particular documents. And machine translation is only to be used for certain types of ... have been induced by a wrong use of M.T. Aware of the necessity of differentiating the documents, people res- ponsible for translation proposed several types of typologi...

Ngày tải lên: 08/03/2014, 18:20

... the amount of mem- ory used, we discount every count by a constant d, which we set to 5. This has a dual effect of reducing the amount of memory needed to hold co-occurrence counts by removing ... by first performing bottom-up biparsing to create a chart of probabilities, then performing top- down sampling of a new tree based on the probabil- ities in this chart. An example of...

Ngày tải lên: 16/03/2014, 19:20

... words that are translations of the English word created by tak- ing all tokens in es t together. C(s, t) denotes the set of Chinese words that are translations of any of the English words ... linguistic grammars are imposed by this model. The translation channel is characterized by two sets of parameters: translation and alignment prob- abilities, l The transl...

Ngày tải lên: 17/03/2014, 07:20

... level. None use a significant amount of semantic information (though all claim to use some). Most if not all perform as "idiots savants', making use of enormous amounts of very unsophisticated ... to translation than simple analysis/synthesis (an almost prima facie proof of the necessity for Transfer). What this means is that the development of translatio...

Ngày tải lên: 17/03/2014, 19:21

... which uses a shallow parser, syntactic parsing is not necessary in most cases because of the similarities in word orders. Also, the lexical semantic ambiguity is usually preserved so, none of these ... and Spanish↔Portugese (Garrido-Alenda et al., 2003). Most of these implementations use similar modules: a morphological analyzer, a part -of- speech tagger, a bilingual transfer diction...

Ngày tải lên: 23/03/2014, 18:20