Báo cáo khoa học: "Improved Word-Level System Combination for Machine Translation" doc

... the system generated by the boosting- based system combination. The points at itera- tion 1 stand for the performance of the baseline systems. We see, first of all, that all the three systems ... that the boosting-based system combination seems to be more helpful to the phrase-based system than to the Hiero system and the syntax-based system. For the phrase-based syste...

Ngày tải lên: 30/03/2014, 21:20

... learning model. 5.2 Systems and Evaluation Method We used two commercial RBMT systems in our experiments: System A for Chinese-English bidi- rectional translation and System B for English- Chinese ... Thus, for each system, we can get three different translations for each input. These differ- ent translations can serve as pseudo references for the outputs of other systems. In o...

Ngày tải lên: 23/03/2014, 16:21

... Parsing for Machine Translation Michel Galley Computer Science Department Stanford University Stanford, CA 94305-9020 mgalley@cs.stanford.edu Christopher D. Manning Computer Science Department Stanford ... Introduction Hierarchical approaches to machine translation have proven increasingly successful in recent years (Chiang, 2005; Marcu et al., 2006; Shen et al., 2008), and often outper...

Ngày tải lên: 20/02/2014, 07:20

... existing tools. For stemming we use the TreeTagger (Schmid, 1994) for German and the Snowball stemmer 1 for Finnish. A vari- ety of ways for compound splitting have been in- vestigated in machine translation ... applied before training and after gener- ating the output in the target language. Normaliza- tion of English/German inflectional morphology to base forms for the purpose of...

Ngày tải lên: 22/02/2014, 02:20

... phrasal system For the phrasal system, we performed integration only with Method 1, using the top 1 or 100- best translations. This is the most straightforward method for combining with any system, ... %). 4 Machine translation systems and data We integrated the inflection prediction model with two types of machine translation systems: systems that make use of syntax and surface ph...

Ngày tải lên: 08/03/2014, 01:20

... 2007. c 2007 Association for Computational Linguistics Tailoring Word Alignments to Syntactic Machine Translation John DeNero Computer Science Division University of California, Berkeley denero@berkeley.edu Dan ... Klein Computer Science Division University of California, Berkeley klein@cs.berkeley.edu Abstract Extracting tree transducer rules for syntac- tic MT systems can be hindered...

Ngày tải lên: 08/03/2014, 02:21

... disambigua- tion (WSD) systems can help to improve the performance of statistical machine transla- tion (MT) systems. In this paper, we suc- cessfully integrate a state-of-the-art WSD system into a state-of-the-art ... hierarchical phrase-based MT system, Hiero. We show for the first time that integrating a WSD sys- tem improves the performance of a state-of- the-art statistical MT sys...

Ngày tải lên: 08/03/2014, 02:21

... more information than the corre- sponding bag of lexical items before parsing. Its elements get enriched with additional informa- tion instantiated during the parsing process. In- formation ... lexicon was used for content words. Only a bilingual lexi- con for closed class words and a set of bilingual templates were used. Therefore, new bilingual entries were obtained for all th...

Ngày tải lên: 08/03/2014, 06:20

... t b rooted in ε b do for all alignments α of the children of t a and t b do β(ε a ,ε b ) += P elem (t a |ε a )P align (α|ε i )  (i,j)∈α β(ε i ,ε j ) end for end for end for end for end for The outer ... k 1 ,l 1 k m ,l m do β(ε i ,k,l)+= P order (ρ|ε i )  m j=1 β(ε j ,k j ,l j ) end for end for end for end for This algorithm has computational complexity O(|T |N m+2 ), w...

Ngày tải lên: 17/03/2014, 06:20

... 312–319, Prague, Czech Republic, June 2007. c 2007 Association for Computational Linguistics Improved Word-Level System Combination for Machine Translation Antti-Veikko I. Rosti and Spyros Matsoukas ... network for the source sentence , is the number of translation systems, is the th system weight, is the accumulated confidence for word produced by system between nodes and...

Ngày tải lên: 31/03/2014, 01:20