Báo cáo khoa học: "A Discriminative Global Training Algorithm for Statistical MT" potx

... ACL, pages 721–728, Sydney, July 2006. c 2006 Association for Computational Linguistics A Discriminative Global Training Algorithm for Statistical MT Christoph Tillmann IBM T.J. Watson Research ... parsing, and the novel training algorithm presented in this pa- per is actually most similar to work on training al- gorithms presented for these task, e.g. the on-line trai...

Ngày tải lên: 31/03/2014, 01:20

... 2008. c 2008 Association for Computational Linguistics A Discriminative Latent Variable Model for Statistical Machine Translation Phil Blunsom, Trevor Cohn and Miles Osborne School of Informatics, University ... means of training and de- coding. Section 4 reports our experimental setup and results, and finally we conclude in Section 5. 2 Challenges for Discriminative SMT Discri...

Ngày tải lên: 23/03/2014, 17:20

... A Best-First Search Algorithm for Generating Referring Expressions Helmut Horacek Uniyersitat des Saarlandes, FR 6.2 Informatik Postfach 151150, D-66041 Saarbdicken, ... except the intended referent(s). Several algorithms have been developed for this purpose, differing in terms of computational efficiency, quality and coverage. For identifying sets of objects rather ... considerable...

Ngày tải lên: 22/02/2014, 02:20

... defin- ing the feature vector is needed for the search in Section 3: the contribution of the ’negative’ fea- tures for c = 0 is only computed when Eq. 1 is evaluated for the highest scoring final hypothesis in ... maxent training algo- rithm in (Tillmann and Zhang, 2007). 3 Beam Search Algorithm We process the comparable data at the sentence level: sentences are indexed based on their...

Ngày tải lên: 17/03/2014, 02:20

... efficient PFS algorithm. At the beginning of each round for feature se- lection, a uniform prior distribution is always assumed for the new CME model. A more pre- cise description of the PFS algorithm ... algorithm that addresses the feature space size limitation. The algorithm is implemented on top of the Selective Gain Com- putation (SGC) algorithm (Zhou et al., 2003), whi...

Ngày tải lên: 17/03/2014, 04:20

... standing for X spanning f j i . We choose b and β to balance speed and performance on our development set. For our experiments, we set b = 40, β = 10 −1 for X cells, and b = 15, β = 10 −1 for S ... f k ∼ e k  for some k ∈ [i, j] and k  ∈ [i  , j  ]; 2. f k  e k  for all k ∈ [i, j] and k   [i  , j  ]; 3. f k  e k  for all k  [i, j] and k  ∈ [i  , j  ]. Next, we fo...

Ngày tải lên: 17/03/2014, 05:20

... clustering algorithm to ensure comparability. 4.3 Testing the Two-stage Algorithm Table 8 shows the results of the Two-stage algorithm for our data sets. The maximally effective cut of point for all ... however, assume text to be in perfect (some even vowelised) form, forcing the need for editing prior to processing. Finally, the success of these algorithms depends critically on r...

Ngày tải lên: 17/03/2014, 07:20

... A simple pattern-matching algorithm for recovering empty nodes and their antecedents ∗ Mark Johnson Brown Laboratory for Linguistic Information Processing Brown University Mark Johnson@Brown.edu Abstract This ... good average performance on all empty nodes if it performs well on the most frequent types of empty nodes, and conversely, a system will perform poorly on average if it does no...

Ngày tải lên: 17/03/2014, 08:20

... adopting it for word segmentation. For example, since word seg- mentation is merely a preprocessing task for a wide variety of further tasks such as parsing, information extraction, and information ... therefore need only define an appropriate rule syntax for transforming this initial approxima- 3The "existing" algorithm does not need to be a large or even accurate s...

Ngày tải lên: 17/03/2014, 23:20

... with Shared Nodes (Lichte, 2007)), or TT-MCTAG for short. For some of the above formalisms the word recognition problem is NP-hard. This has been shown for non-local MCTAG (Rambow and Satta, 1992), ... derivation tree without deciding, for ev- ery occurrence of some argument β, which of the h(β)-nodes represents its head. Therefore we pro- pose to reformulate (SN-TTL). For a node v...

Ngày tải lên: 23/03/2014, 16:21