Báo cáo khoa học: "A TRANSFER MODEL USING A TYPED FEATURE STRUCTURE REWRITING SYSTEM WITH INHERITANCE" pot

Báo cáo khoa học: "A TRANSFER MODEL USING A TYPED FEATURE STRUCTURE REWRITING SYSTEM WITH INHERITANCE" pot

Báo cáo khoa học: "A TRANSFER MODEL USING A TYPED FEATURE STRUCTURE REWRITING SYSTEM WITH INHERITANCE" pot

... A TRANSFER MODEL USING A TYPED FEATURE STRUCTURE REWRITING SYSTEM WITH INHERITANCE R6mi Zajac ATR Interpreting Telephony Research Laboratories Sanpeidani lnuidani, Seika-cho~ Soraku-gun, ... 619-02, Japan [zajac%atr-ln.atr.junet@uunet.un.net] ABSTRACT We propose a model for transfer in machine translation which uses a rewriting system for typed feat...

Ngày tải lên: 17/03/2014, 20:20

6 264 0
Báo cáo khoa học: "Finding Word Substitutions Using a Distributional Similarity Baseline and Immediate Context Overlap" potx

Báo cáo khoa học: "Finding Word Substitutions Using a Distributional Similarity Baseline and Immediate Context Overlap" potx

... distributional similarity baseline (a sub- set of Wikipedia) in an attempt to show that a good semantic parse and adequate filtering can provide reasonable performance even on domains where data is sparse. ... the head ‘rescue’, lemma:rescue arg:ARG2 var:bank which indicates that ‘bank’ is object of the head ‘rescue’, and lemma:failing arg:ARG1 var:bank which indicates that the argument of...

Ngày tải lên: 08/03/2014, 21:20

9 248 0
Báo cáo khoa học: "Accurate Collocation Extraction Using a Multilingual Parser" docx

Báo cáo khoa học: "Accurate Collocation Extraction Using a Multilingual Parser" docx

... Spanish and Italian (sec- tion 3). Then we present in sections 4 and 5 a com- parative evaluation experiment proving that a hy- brid approach leads to more accurate results than a classical approach ... with parsing. Its author had to simulate parsing because of the lack, at the time, of parsing tools for Ger- man. Our report, that concerns an actual system and a large data set, v...

Ngày tải lên: 17/03/2014, 04:20

8 261 0
Báo cáo khoa học: "Fast Semantic Extraction Using a Novel Neural Network Architecture" docx

Báo cáo khoa học: "Fast Semantic Extraction Using a Novel Neural Network Architecture" docx

... is labeled for each particular verb as so-called frames. Addition- ally, semantic roles can also be labeled with one of 13 ARGM adjunct labels, such as ARGM-LOC or ARGM-TMP for additional locational ... PropBank gold annotation); as well as several other features (predicate, head word, verb sub-categorization, ). The authors of (Pradhan et al., 2004) used a similar structure, but added m...

Ngày tải lên: 17/03/2014, 04:20

8 303 0
Báo cáo khoa học: "Automatic Story Segmentation using a Bayesian Decision Framework for Statistical Models of Lexical Chain Features" pdf

Báo cáo khoa học: "Automatic Story Segmentation using a Bayesian Decision Framework for Statistical Models of Lexical Chain Features" pdf

... Lexical Chain Features 4.1 Chain starts and ends We follow (Chan et al. 2007) to model the lexi- cal chain starts and ends at a story boundary with a statistical distribution. We apply a window ... a Single Lexical Chain Feature Given an utterance boundary with the lexical chain feature, X, we compare the conditional probabilities of observing a boundary, B, or non- b...

Ngày tải lên: 23/03/2014, 17:20

4 402 1
Báo cáo khoa học: "Linear Text Segmentation using a Dynamic Programming Algorithm" potx

Báo cáo khoa học: "Linear Text Segmentation using a Dynamic Programming Algorithm" potx

... (Heinonen, 1998) and Utiyama and Isahara (Utiyama and Isa- hara, 2001). Finally, other researchers use probabilistic ap- proaches to text segmentation including the use of hidden Markov models (Yamron et al., 1999), ... Linear Text Segmentation using a Dynamic Programming Algorithm Athanasios Kehagias Dept. of Math., Phys. and Comp. Sciences Aristotle Univ of Thessaloniki GREECE kehagia...

Ngày tải lên: 31/03/2014, 20:20

8 348 0
Tài liệu Báo cáo khoa học: "An Efficient Parallel Substrate for Typed Feature Structures on Shared Memory Parallel Machines" docx

Tài liệu Báo cáo khoa học: "An Efficient Parallel Substrate for Typed Feature Structures on Shared Memory Parallel Machines" docx

... existing CSAs. All CSAs can basi- cally perform concatenation in parallel and in- dependent way. Then, the name-concatenator waits for the name-concatenator-sub to return concatenated names, and ... its heap: • shared heap • local heap A local heap is used for temporary operations during the computation inside a CSA. A CSA cannot read/write local heap of other CSAs. A shared...

Ngày tải lên: 20/02/2014, 18:20

7 429 0
Báo cáo khoa học: Actin-binding domain of mouse plectin Crystal structure and binding to vimentin pot

Báo cáo khoa học: Actin-binding domain of mouse plectin Crystal structure and binding to vimentin pot

... to pKAB1, using primer pairs pFS2 forward (5¢-CCGGAATTCATGTGGACCAGGTCTGTG-3¢), and pFS2 reverse (5¢-CCGGAATTCCTCAGTGTTGATGG CGTC-3¢), and pFS3 forward (5¢-CCGGAATTCTTCAA GAACACCCGC-3¢), and pFS3 ... crystallographic dimer observed in the asymmetric unit was probably an artefact of crystallization rather than a dimerization product. Although CH subdomains forming a canonical ABD structur...

Ngày tải lên: 07/03/2014, 15:20

12 477 0
Tài liệu Báo cáo khoa học: "Lexical transfer using a vector-space model" doc

Tài liệu Báo cáo khoa học: "Lexical transfer using a vector-space model" doc

... Lexical transfer using a vector-space model Eiichiro SUMITA ATR Spoken Language Translation Research Laboratories 2-2 Hikaridai, Seika, Soraku Kyoto 619-0288, Japan sumita@slt.atr.co.jp ... from case-frame representations of simple sentences with a thesaurus for generalization (Akiba et. al., 1996 and Tanaka, 1995); (2) approaches using structural matching: to obtain...

Ngày tải lên: 20/02/2014, 18:20

7 654 0
Tài liệu Báo cáo khoa học: "An Alignment Algorithm using Belief Propagation and a Structure-Based Distortion Model" pdf

Tài liệu Báo cáo khoa học: "An Alignment Algorithm using Belief Propagation and a Structure-Based Distortion Model" pdf

... 1: A classical example the variables represented with a Factor Graph and with a Bayesian Network. Mathematically, the Bayesian Network imply that the joint probabil- ity has the following factorization: ... segmented all the Japanese data with the automatic segmenter Juman (Kurohashi and Nagao, 1994). There is a caveat to this evaluation, though. The reason is that the segmentat...

Ngày tải lên: 22/02/2014, 02:20

9 456 0
w