Báo cáo khoa học: "Lattice Parsing to Integrate Speech Recognition and Rule-Based Machine Translation" pdf

Báo cáo khoa học: "Lattice Parsing to Integrate Speech Recognition and Rule-Based Machine Translation" pdf

Báo cáo khoa học: "Lattice Parsing to Integrate Speech Recognition and Rule-Based Machine Translation" pdf

... April 2009. c 2009 Association for Computational Linguistics Lattice Parsing to Integrate Speech Recognition and Rule-Based Machine Translation Selçuk Köprü AppTek, Inc. METU Technopolis Ankara, ... novel approach to integrate speech recognition and rule- based machine translation by lattice pars- ing. The presented approach is hybrid in two senses. First, it comb...

Ngày tải lên: 31/03/2014, 20:20

9 295 0
Báo cáo khoa học: "Discriminative Strategies to Integrate Multiword Expression Recognition and Parsing" docx

Báo cáo khoa học: "Discriminative Strategies to Integrate Multiword Expression Recognition and Parsing" docx

... be easily integrated in the MWE sequence. Constant and Sigogne (2011) proposed to combine MWE seg- mentation and part-of -speech tagging into a single sequence labelling task by assigning to each token ... parameter vector θ and a feature vector f: V θ (p) = θ.f(p) = m  j=1 θ j .f j (p) where f j (p) corresponds to the number of occur- rences of the feature f j in the parse p. A...

Ngày tải lên: 16/03/2014, 19:20

9 286 0
Báo cáo khoa học: "Dependency Parsing of Hungarian: Baseline Results and Challenges" potx

Báo cáo khoa học: "Dependency Parsing of Hungarian: Baseline Results and Challenges" potx

... 933–939. Szil ´ ard Iv ´ an, R ´ obert Orm ´ andi, and Andr ´ as Kocsor. 2007. Magyar mondatok SVM alap ´ u szintaxis elemz ´ ese [SVM-based syntactic parsing of Hun- garian sentences]. In V. Magyar ... Conference on Language Resources and Evaluation (LREC ’06). D ´ aniel Varga, P ´ eter Hal ´ acsy, Andr ´ as Kornai, Viktor Nagy, L ´ aszl ´ o N ´ emeth, and Viktor Tr ´ on. 2005. Par-...

Ngày tải lên: 17/03/2014, 22:20

11 386 0
Báo cáo khoa học: "Attacking Parsing Bottlenecks with Unlabeled Data and Relevant Factorizations" pdf

Báo cáo khoa học: "Attacking Parsing Bottlenecks with Unlabeled Data and Relevant Factorizations" pdf

... sibling and grandparent factorizations described above–for Conversion 1, sibling scoring may help conjunctions and grandparent scoring may help prepositions, and for Conversion 2, grandparent scoring ... (for prepositions) will lead to the largest improvements. For the phrase dogs and cats, edge-based counts would measure the associations between dogs and and, and and and cats...

Ngày tải lên: 23/03/2014, 14:20

9 277 0
Báo cáo khoa học: From meiosis to postmeiotic events: Alignment and recognition of homologous chromosomes in meiosis ppt

Báo cáo khoa học: From meiosis to postmeiotic events: Alignment and recognition of homologous chromosomes in meiosis ppt

... transcribed rDNA loci and histone genes [36]. A previous model proposed roles for transcription and for a specialized transcription fac- tory in homologous chromosome recognition and pairing [37,38]. ... attached to a specific transcription factory, in which transcriptional machinery proteins are aggregated, and those DNA regions that are not undergoing transcription pro- trude fro...

Ngày tải lên: 29/03/2014, 08:20

6 473 0
Tài liệu Báo cáo khoa học: "Modified Distortion Matrices for Phrase-Based Statistical Machine Translation" doc

Tài liệu Báo cáo khoa học: "Modified Distortion Matrices for Phrase-Based Statistical Machine Translation" doc

... the decoder to modify the distortion matrix just before starting the search. As usual, the distortion matrix is queried by the distortion penalty generator and by the hypothesis expander 9 . 7.1 ... chunk- based rules following Bisazza and Federico (2010). Shallow syntax chunking is indeed a lighter and simpler task compared to full parsing, and it can be used to constrain the...

Ngày tải lên: 19/02/2014, 19:20

10 473 0
Tài liệu Báo cáo khoa học: "Improving Word Representations via Global Context and Multiple Word Prototypes" pdf

Tài liệu Báo cáo khoa học: "Improving Word Representations via Global Context and Multiple Word Prototypes" pdf

... with vectors that capture semantic and syntac- tic information of words. These representations can be used to induce similarity measures by computing distances between the vectors, leading to many ... each word is only repre- sented with one vector, which clearly fails to capture homonymy and polysemy. Reisinger and Mooney (2010b) introduced a multi-prototype VSM where word sense...

Ngày tải lên: 19/02/2014, 19:20

10 494 0
Tài liệu Báo cáo khoa học: "Unsupervised Search for The Optimal Segmentation for Statistical Machine Translation" doc

Tài liệu Báo cáo khoa học: "Unsupervised Search for The Optimal Segmentation for Statistical Machine Translation" doc

... correspond to different random orders in processing the data (Creutz and Lagus, 2007). are affected by the decision in the current step. This leads to a sequential search and does not lend itself to ... as in Creutz and Lagus (2007). To sum- marize briefly, the prior P (M f ) is assumed to only depend on the frequencies and lengths of the indi- vidual morphs, which are also a...

Ngày tải lên: 20/02/2014, 04:20

6 446 0
Tài liệu Báo cáo khoa học: "Topological Ordering of Function Words in Hierarchical Phrase-based Translation" pdf

Tài liệu Báo cáo khoa học: "Topological Ordering of Function Words in Hierarchical Phrase-based Translation" pdf

... Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 324–332, Suntec, Singapore, 2-7 August 2009. c 2009 ACL and AFNLP 1 2 3 1 1 2 3 { } 324 X → γ, α, ∼ X

Ngày tải lên: 20/02/2014, 07:20

9 472 1
Tài liệu Báo cáo khoa học: "Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop" pdf

Tài liệu Báo cáo khoa học: "Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop" pdf

... gets tokenized correctly, independently of the number of resulting tokens; the token-based measures refer to the four token fields into which the ATB splits each word determines the ATB tokenization. ... corpora as TR1 and TR2, and to the test corpora as, TE1 and TE2. We report results on both TE1 and TE2 be- cause of the differences in the two parts of the ATB, both in terms of or...

Ngày tải lên: 20/02/2014, 15:20

8 385 0
w