Báo cáo khoa học: "An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility via semantic frames" pdf

... 19-24, 2011. c 2011 Association for Computational Linguistics MEANT: An inexpensive, high-accuracy, semi-automatic metric for evaluating translation utility via semantic frames Chi-kiu Lo and ... Workshop on Statistical Ma- chine Translation and Metrics for Machine Translation. In Proceedings of the Joint 5th Workshop on Statistical Machine Translation and Metri...

Ngày tải lên: 07/03/2014, 22:20

... model-theoretic semantics and therefore no concept of semantic equivalence. On the other hand, we do not need to solve the full semantic equivalence problem, as we only want to compare formulas that ... in- verted rule.) We formalise this rewriting-based notion of equivalence as follows. The definition uses the ab- breviation x [1,k) for the sequence x 1 , ,x k−1 , and x (k,n] for x k+...

Ngày tải lên: 20/02/2014, 12:20

... possibilities for fine-tuning; therefore the comparison should be fair. The comparison show that performance-wise, the monolink algorithm is between the model 2 and the model 3 for English/French. ... syntactic trees for every sentences. For English,we used the Dan Bikel im- plementation of the Collins parser (Collins, 2003). For French, the SYGMART parser (Chauch ´ e, 1984) and for...

Ngày tải lên: 22/02/2014, 02:20

... entry for a next state, while constructing a constituent structure by instantiating it. No search for unifiable categories is involved during parsing. procedure CLOSURE(I); begin repeat for ... search for GOTO table entries during parsing. 1 Introduction The LR method is known to be a very efficient parsing algorithm that involves no searching or backtracking. However, recen...

Ngày tải lên: 22/02/2014, 10:20

... that most often (125 cases/141 for rule [b], 50 cases/52 for rule [c]) the correct parsing isolates the second sub-group,noun2 adj for rule [b], noun2 prep noun3 for rule [c] (see the top left ... eliminating the hand coding of semantic information by exploiting an already available source of information. This method differs from ours in that the source of information is a mach...

Ngày tải lên: 09/03/2014, 01:20

... algorithm for transforming LCFRS with fan-out at most 2 into a binary form, whenever this is possible. This results in asymptotical run-time improvement for known parsing algorithms for this class. 1 ... Introduction Since its early years, the computational linguistics field has devoted much effort to the development of formal systems for modeling the syntax of nat- ural language. Ther...

Ngày tải lên: 23/03/2014, 16:21

... of features of the complex word forms. Let us assume, that the right segmentation for the sentence is provided to us – for example: b clm hn‘im – as is the case for English text. In such a way, ... tagged, according to the trained model, in order to form a tag distribution for each unknown word, according to its context and its form. Finally, the tag for each unknown word were selec...

Ngày tải lên: 23/03/2014, 18:20

... Department Stanford University Stanford, CA 94305 vijayk@cs.stanford.edu Christopher D. Manning Computer Science Department Stanford University Stanford, CA 94305 manning@cs.stanford.edu Abstract This paper ... baseline CRF using local information alone, whose performance is close to the best published local CRF models, for Named Entity Recognition 3 Label Consistency The intuition for mo...

Ngày tải lên: 31/03/2014, 01:20

... frameworks can thus be used for treebank conversion with little modification. Matching Metric for Treebank Conversion The matching metric or matching score for tree- bank conversion is ... therefore, the annotated information to the target treebank can be anything inherent from the target system; the bracket information of the original treebank thus provides useful informa...

Ngày tải lên: 31/03/2014, 06:20

... results o f t_he automatic formatting routines. Postediting is expected for the output t~. The system does not expect (or provide for) human intervention during the actual translation phase. Pre-processing ... entries supply necessary information for the analysis and/or synthesis of these it~m~ during the mach/x~ translation process. Most entries are reasonably s4~le, but e...

Ngày tải lên: 01/04/2014, 00:20