Báo cáo " Isolated Handwritten Vietnamese Character Recognition with Feature Extraction and Classifier Combination " docx

Báo cáo " Isolated Handwritten Vietnamese Character Recognition with Feature Extraction and Classifier Combination " docx

Báo cáo " Isolated Handwritten Vietnamese Character Recognition with Feature Extraction and Classifier Combination " docx

... 123 Isolated Handwritten Vietnamese Character Recognition with Feature Extraction and Classifier Combination Le Anh Cuong * , Ngo Tien Dat, Nguyen Viet Ha University of Engineering and Technology, ... previous studies on Vietnamese handwritten recognition [9, 23] on both aspects of feature extraction and classifier combination. 4. Feature extracti...

Ngày tải lên: 14/03/2014, 13:20

17 345 0
Tài liệu Báo cáo khoa học: "Learning Word Senses With Feature Selection and Order Identification Capabilities" pdf

Tài liệu Báo cáo khoa học: "Learning Word Senses With Feature Selection and Order Identification Capabilities" pdf

... to avoid the bias to- ward the selection of fewer features, since with fewer features, there are more occurrences without features in contexts, and their context vectors will be zero valued, which ... 0.1260 Table 4: Mutual information between feature subset and class label with freq based feature ranking. Word Cont. Size of MI Size of MI wind. feature ×10 −2 feature ×10 −2 si...

Ngày tải lên: 20/02/2014, 16:20

8 463 0
Báo cáo khoa học: "Recognizing Textual Parallelisms with edit distance and similarity degree" docx

Báo cáo khoa học: "Recognizing Textual Parallelisms with edit distance and similarity degree" docx

... Textual Parallelisms with edit distance and similarity degree Marie Gu ´ egan and Nicolas Hernandez LIMSI-CNRS Universit´e de Paris-Sud, France guegan@aist.enst.fr | hernandez@limsi.fr Abstract Detection ... a string editing distance (Wagner and Fischer, 1974) and a tree editing distance 1 (Zhang and Shasha, 1989). Section 4 discusses and evaluates these methods and their rele...

Ngày tải lên: 24/03/2014, 03:20

8 258 0
Báo cáo khoa học: "Speech emotion recognition with TGI" pot

Báo cáo khoa học: "Speech emotion recognition with TGI" pot

... we arrived to a meaningful combination of methods from different pattern recognition paradigms. 4.2 A combination of statistical and syntactic recognition Syntactic recognition is a form of pattern ... transmitted with segmental features and others with prosodic (Barra, et al., 1993). A coefficient of 1.5 on the prosodic branches brought 2% of improvement of recognition for...

Ngày tải lên: 08/03/2014, 21:20

7 231 0
Tài liệu Báo cáo khoa học: "K-means Clustering with Feature Hashing" docx

Tài liệu Báo cáo khoa học: "K-means Clustering with Feature Hashing" docx

... classes and randomly drew 100 documents for each class. We used unigrams and bigrams as features and ran our method for various hash sizes m (Figure 1). The number of unigrams is 33,017 and bigrams ... realesed in 2007. Ganchev and Dredze (2008) named their hashing trick random feature mixing and empirically sup- ported it by experimenting on NLP tasks. It is simi- lar to featu...

Ngày tải lên: 20/02/2014, 05:20

5 601 0
Báo cáo khoa học: "A Dialogue System with Contextually Appropriate Spoken Output Intonation" docx

Báo cáo khoa học: "A Dialogue System with Contextually Appropriate Spoken Output Intonation" docx

... the Focus within Theme and Rheme. A Rheme must always contain a Focus, while Themes can be unmarked (without Focus) or marked (with Focus). Tunes are obtained by combining accents with appropriate ... FESTIVAL and MARY into GoDiS is shown in Fig. 4. The interface be- tween GoDiS and MARY/FESTIVAL works as follows: The output module of GoDiS takes a string annotated with IS par...

Ngày tải lên: 17/03/2014, 22:20

4 340 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

... dogs and cats, edge-based counts would measure the associations between dogs and and, and and and cats, but never any web counts that include both dogs and cats. For the phrase ate spaghetti with ... sibling and grandparent factorizations described above–for Conversion 1, sibling scoring may help conjunctions and grandparent scoring may help prepositions, and for Conversion...

Ngày tải lên: 23/03/2014, 14:20

9 277 0
Báo cáo khoa học: "Combining POMDPs trained with User Simulations and Rule-based Dialogue Management in a Spoken Dialogue System" docx

Báo cáo khoa học: "Combining POMDPs trained with User Simulations and Rule-based Dialogue Management in a Spoken Dialogue System" docx

... to spoken dialogue systems that includes rule-based and trainable dialogue managers, spoken language understanding and generation modules, and a compre- hensive dialogue system architecture. ... simula- tions. To optimize Q and populate the policy with ex- pected values, the learner needs to explore un- tried actions (system moves) to gain more expe- riences, and combine this wit...

Ngày tải lên: 23/03/2014, 17:20

4 269 0
Báo cáo khoa học: "Enhancing electronic dictionaries with an index based on associations" docx

Báo cáo khoa học: "Enhancing electronic dictionaries with an index based on associations" docx

... appropriate in a given context. Obviously, readers and writers come to the dictionary with different mindsets, information and expectations concerning input and output. While the decoder can provide ... network composed of nodes (words and con- cepts) and links (associations), with either being able to activate the other 5 . Finding a word in- volves entering the network a...

Ngày tải lên: 23/03/2014, 18:20

8 280 0
Báo cáo khoa học: "Complementing Word Net with Roget''''s and Corpus-based Thesauri for Information Retrieval" pdf

Báo cáo khoa học: "Complementing Word Net with Roget''''s and Corpus-based Thesauri for Information Retrieval" pdf

... co-occurence of words a and b with the indepen- dent probabilities of occurrence of a and b (Church and Hanks, 1990). P(a, b) I(a, b) = log P(a)P(b) where the probabilities of P(a) and P(b) are ... only one parse tree with highest possibility. During the parsing process, the parser keeps the unexpanded active nodes in a heap, and always expands the active node with...

Ngày tải lên: 31/03/2014, 21:20

8 263 0
w