Báo cáo khoa học: "Modelling lexical redundancy for machine translation" doc

... 969–976, Sydney, July 2006. c 2006 Association for Computational Linguistics Modelling lexical redundancy for machine translation David Talbot and Miles Osborne School of Informatics, University of Edinburgh 2 ... language. We quantify redundancy among source types by the similarity of their distributions over target types. We propose a language- independent framework for minim...

Ngày tải lên: 17/03/2014, 04:20

... N for i = 1; i ≤ M; i = i +1 do for j = 1; j ≤ N; j = j +1 do for k = 1; k ≤ i; k = k +1 do for m = 1; m ≤ j; m = m +1 do score i,j,k,m = max{score i−1,j,k,m ,score i,j−1,k,m } ; end for end for score i,j,i,j = max n=1,M;p=1,N {score i,j,i,j , ... |ref|; for i = 1; i ≤ M; i = i +1 do for j = 1; j ≤ N; j = j +1 do for k = 1; k ≤ i; k = k +1 do for m = 1; m ≤ j; m = m +1 do...

Ngày tải lên: 08/03/2014, 02:21

... of several formats. Format S (specifiers) in- volves whole constituents, including symbols and subscripts. Format A is for text, and in- volves only symbols. Both format S and for- mat A ... that calls for reading in format S from a designated channel, the next constituent from the input is brought into the workspace where it replaces the designated numbered constituent. For ex...

Ngày tải lên: 16/03/2014, 19:20

... the av- erage accuracy for each reordering distance d. It shows that even for long distance reordering, the DPR model still performs well, while the MLE baseline usually performs badly (more than ... kinds of information extracted from the Input: The samples  o, φ( ¯ f j , ¯e i )  N n=1 , step size η Initialization: k = 0; w o,k = 0 ∀o ∈ Ω; Repeat for n = 1, 2, . . . , N do for o ...

Ngày tải lên: 17/03/2014, 02:20

... framework, it is straightforward to encode the morphological properties of a word, in addition to its surface inflected form. For example, for a particular inflected word form y t and its con- text, ... USA hisamis@microsoft.com Abstract We present a novel method for predicting in- flected word forms for generating morpho- logically rich languages in machine trans- lation. We utilize a...

Ngày tải lên: 17/03/2014, 04:20

... B LEU: a Method for Au- tomatic Evaluation of Machine Translation. In Proc. of ACL’02, 311–318. Michael Pozar and Eugene Charniak. 2006. Bllip: An Improved Evaluation Metric for Machine Translation. ... the Association for Computational Linguistics, pages 108–117, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Automatic Evaluation Method for...

Ngày tải lên: 23/03/2014, 16:20

... translation performance obtained by the training phase. 2 For decoding, we prohib- ited Moses form performing character reordering (distortion). While reordering may be needed for translation, ... The system’s overall accuracy is about 72% for top-1 results and 84% for top-20 results. This method is restricted to transliterating NEs, and performs best for person names. As noted abov...

Ngày tải lên: 24/03/2014, 03:20

... approach. Similar results could be expected for other suffi- ciently related languages as well. The paper con- centrates on the linguistic grounds for adopting the approach proposed. 1. INTRODUCTION ... problem, the efforts of computational linguists have been main- ly directed to the process of analysis: a unique analysis is searched (semantical and/or world knowledge informati...

Ngày tải lên: 17/03/2014, 19:21

... poly- nomial time solution for any of these hard problems (unless P = NP and P #P = P), our results highlight and justify the need for developing polynomial time ap- proximations for these computations. ... complexity. 1 Introduction Statistical Machine Translation is a data driven machine translation technique which uses proba- bilistic models of natural language for automatic tr...

Ngày tải lên: 31/03/2014, 20:20

... before, AltaVista was used as search engine. A baseline for the answer validation experiment was defined by considering how often an answer oc- curs in the top 10 documents among those (1000 for ... a question can be quantitatively estimated by exploit- ing the redundancy of Web information. The hy- pothesis is that the number of documents that can be retrieved from the Web in which the...

Ngày tải lên: 08/03/2014, 07:20