Báo cáo khoa học: "Minimum Risk Annealing for Training Log-Linear Models∗" doc
... 2006. c 2006 Association for Computational Linguistics Minimum Risk Annealing for Training Log-Linear Models ∗ David A. Smith and Jason Eisner Department of Computer Science Center for Language and Speech ... machinery to training log-linear combinations of models for dependency parsing and for machine translation (§6). Finally, we note the connections of minimum risk...
Ngày tải lên: 31/03/2014, 01:20
... three lectures is- used for estimating the optimal word block length for representing nodes, the threshold distances for discarding node edges, the number of uniform chunks for estimating tf-idf ... to specialized technical vocabulary and lack of in-domain spoken data for training. Finally, pedagogical considerations call for fluent transitions between different topics in a lectu...
Ngày tải lên: 20/02/2014, 11:21
... error reduction. Results are for dependency parsing on the dev set for iters:5 ,training- k:1. tal errors break down by gold head. For example, the 12.1% total error reduction for attachments of an IN ... grammar 6 Their README specifies training- k:5 iters:10 loss- type:nopunc decode-type:proj’, which we used for all final ex- periments; we used the faster training- k:1 iters:5’ sett...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "An Approximate Approach for Training Polynomial Kernel SVMs in Linear Time" doc
... Association for Computational Linguistics An Approximate Approach for Training Polynomial Kernel SVMs in Linear Time Yu-Chieh Wu Jie-Chi Yang Yue-Shi Lee Dept. of Computer Science and Information ... did not use feature conjunctions. However, the training and testing time costs for polynomial kernel SVM is far slow than the linear kernel. For example, it took one day to...
Ngày tải lên: 20/02/2014, 12:20
Tài liệu Báo cáo khoa học: "A CONNECTIONIST PARSER FOR STRUCTURE UNIFICATION GRAMMAR" docx
... grouping of information, thus expressing the information in- terdependencies. The language which SUG pro- vides for specifying these descriptions allows par- tiality both in the information about ... thereby also forgetting the predications over the nodes. This forgetting operation abstracts away from the existence of the forgotten node in the phrase structure. Once a node is forgot...
Ngày tải lên: 20/02/2014, 21:20
Báo cáo khoa học: "SVD and Clustering for Unsupervised POS Tagging" docx
... map-free information- theoretic criterion—see Gao and Johnson (2008) for details. Although we find M-to-1 to be the most reliable criterion of the three, we include the other two criteria for completeness. ... Table 1 compares the per- formance of SVD2 to other leading models. Fol- lowing Gao and Johnson (2008), the number of induced tags is 17 for PTB17 evaluation and 50 for PTB45...
Ngày tải lên: 07/03/2014, 22:20
Báo cáo khoa học: "Stochastic Iterative Alignment for Machine Translation Evaluation" doc
... 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
Báo cáo khoa học: "A Debug Tool for Practical Grammar Development" doc
... example. 1 Introduction There is an increasing need for syntactical parsers for practical usages, such as information extrac- tion. For example, Yakushiji et al. (2001) extracted argument structures from ... data for the developers to clarify the defects of the grammar statistically. We applied willex to a large-scale HPSG-style grammar as an example. 1 Introduction There is an increa...
Ngày tải lên: 08/03/2014, 04:22
Báo cáo khoa học: "Randomised Language Modelling for Statistical Machine Translation" doc
... hash of event {x, j} under h i BF[h i (x)] ← 1 end for end for end for return BF 3.1 Log-frequency Bloom filter The efficiency of our scheme for storing n-gram statistics within a BF relies on ... bound on qc(x) ∈ S train for j = 1 to M AXQCOUNT do for i = 1 to k do h i (x) ← hash of event {x, j} under h i if BF[h i (x)] = 0 then return j − 1 end if end for end for The probabili...
Ngày tải lên: 17/03/2014, 04:20
Báo cáo khoa học: "THE TEXT SYSTEM FOR NATURAL LANGUAGE GENERATION" doc
... used for TEXT i. 2. 3. 4. identification -requests for definitions attributive -requests for available information constituency -requests for definitions -requests for available information ... detailed attributive information is included. For entities that are very different, only generic class information is included. A combination of this information is included...
Ngày tải lên: 17/03/2014, 19:21