Báo cáo toán học: " Global Bifurcation Results for General Laplacian Problems" pot

Báo cáo khoa học: "Classifying Recognition Results for Spoken Dialog Systems" doc

Báo cáo khoa học: "Classifying Recognition Results for Spoken Dialog Systems" doc

... that the results for TiMBL with default settings are significantly worse than all other results. The other four machine learning re- sults (parameter optimization and feature selection for TiMBL ... 2 show the DET curves for TiMBL and Ripper as compared to the baseline respectively. 4.5 Results The DET curve for TiMBL is almost identical to the baseline. The curve for Ripper, ho...
Ngày tải lên : 23/03/2014, 19:20
  • 8
  • 273
  • 0
Tài liệu Báo cáo khoa học: "An Integrated Environment for Computational Linguistics Experimentation" pot

Tài liệu Báo cáo khoa học: "An Integrated Environment for Computational Linguistics Experimentation" pot

... analy- sis models and methodological concerns. Finally, when other platforms usually enforce the use of a dedicated document format, LinguaStream is able to process any XML document. On the other ... stream, the platform takes care of the scheduling of sub-tasks, and various tools allow the results to be visualised conveniently. Fundamental principles First of all, the platform makes use of...
Ngày tải lên : 22/02/2014, 02:20
  • 4
  • 325
  • 0
Tài liệu Báo cáo khoa học: "A rich environment for experimentation unification grammars" potx

Tài liệu Báo cáo khoa học: "A rich environment for experimentation unification grammars" potx

... are due to C.J. Rupp for being a wil- ling and constructive guinea- pig, as well as for allowing us to plunder his work for German examples. - 189 - A rich environment for experimentation ... into discussion of the under- lying complexity, for which we unfortunately do not have space here, we give an exter- nal form of a lexical entry for some of the senses of the Ger...
Ngày tải lên : 22/02/2014, 10:20
  • 8
  • 367
  • 0
Báo cáo khoa học: "Learning Expressive Models for Word Sense Disambiguation" pot

Báo cáo khoa học: "Learning Expressive Models for Word Sense Disambiguation" pot

... need for a unique representation for all the ex- amples: one attribute is created for every knowl- edge feature and the same structure is used to characterize all the examples. This usually results ... 3, results are very encour- aging: even without being particularly customized for this monolingual task, the ILP approach signif- icantly outperforms the majority sense baseline an...
Ngày tải lên : 08/03/2014, 02:21
  • 8
  • 380
  • 0
Báo cáo khoa học: "A STOCHASTIC PROCESS FOR WORD FREQUENCY DISTRIBUTIONS" pot

Báo cáo khoa học: "A STOCHASTIC PROCESS FOR WORD FREQUENCY DISTRIBUTIONS" pot

... birth rates for word formation processes to the model, neces- sitated by the additional large numbers of rare 277 for word frequency distributions. Unfortunately, comparing the results of ... (1975), have been put forward, all of which have Zipf's law as some special or limiting form. Unrelated to Zipf's law is the lognormal hypothesis, advanced for word fre- quency...
Ngày tải lên : 08/03/2014, 07:20
  • 8
  • 409
  • 0
Báo cáo khoa học: "Using Derivation Trees for Treebank Error Detection" potx

Báo cáo khoa học: "Using Derivation Trees for Treebank Error Detection" potx

... Sheikh NP #a3 qmp summit #b1 S:1.2 NP NP^ $rm Sharm #b2 NP Al$yx The Sheikh For (2a) For (2b) For (2c) A:1.1,left #b3 NP Al$yx The Sheikh A:1.1,left #c3 $rm Sharm Figure 1: Etrees and Derivation Trees for (2abc). tree-substitution, sister-adjunction, ... to compare for inconsistent an- notation, and are computed separately for each in- stance of each nucleus from the full deriva...
Ngày tải lên : 17/03/2014, 00:20
  • 6
  • 292
  • 0
Báo cáo khoa học: "Incremental HMM Alignment for MT System Combination" pot

Báo cáo khoa học: "Incremental HMM Alignment for MT System Combination" pot

... the order of hypotheses. If hypothesis 2 is aligned before hypothesis 1, the final CN will not be good. Therefore, the obser- vation in Rosti et al. (2008) that different order of hypotheses does ... therefore a limit L to the length of se- quences. In general the limit L ≥ 8 would ren- der the tuning/decoding process intolerably slow. We tried the values 5 to 8 for L and the variation of...
Ngày tải lên : 17/03/2014, 01:20
  • 9
  • 263
  • 0
Báo cáo khoa học: "Generalizing Tree Transformations for Inductive Dependency Parsing" potx

Báo cáo khoa học: "Generalizing Tree Transformations for Inductive Dependency Parsing" potx

... corresponding parsing results using MaltParser with transformations for coordination and verb groups are shown in table 4. For SDT, PADT and PDT, the annotation of coordination has been trans- formed from ... training set for this type of transformation. The same generalization over treebanks holds for verb groups too. The last column in table 4 shows that the expected increase in a...
Ngày tải lên : 17/03/2014, 04:20
  • 8
  • 264
  • 0

Xem thêm

Từ khóa: