Báo cáo khoa học: "Syntactic Features and Word Similarity for Supervised Metonymy Resolution" pot

Báo cáo khoa học: "Syntactic Features and Word Similarity for Supervised Metonymy Resolution" pot

Báo cáo khoa học: "Syntactic Features and Word Similarity for Supervised Metonymy Resolution" pot

... Syntactic Features and Word Similarity for Supervised Metonymy Resolution Malvina Nissim ICCS, School of Informatics University of Edinburgh mnissim@inf.ed.ac.uk Katja Markert ICCS, School of Informatics University ... as a metonymy) that “England” and “Scot- land” in (3) and (4) are also metonymic. In order to 2 Due to its regularity, conventional metonymy is also known...

Ngày tải lên: 08/03/2014, 04:22

8 603 0
Tài liệu Báo cáo khoa học: "Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System" pptx

Tài liệu Báo cáo khoa học: "Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System" pptx

... 3 illustrates the PST for the sentences: Where is the Anping-Fort. There are two keywords Where and Anping-Fort and two non-keywords is and the. Note that with 2 non-keywords in the original ... PST as a knowl- edge source for DA detection, we essentially need to model the relationship between the random DA and the random DR. Denote the random DA by X and the random DR by Y . Gi...

Ngày tải lên: 20/02/2014, 05:20

6 555 0
Tài liệu Báo cáo khoa học: "Fast Decoding and Optimal Decoding for Machine Translation" doc

Tài liệu Báo cáo khoa học: "Fast Decoding and Optimal Decoding for Machine Translation" doc

... “spurious” French words. Next, we perform a word- for -word replace- ment of English words (including NULL) by French words, according to the table t(f e ). Finally, we permute the French words. In per- muting, ... hy- pothesis. Pop h, the best hypothesis, off the stack. If h is a complete sentence, output h and terminate. For each possible next word w, extend h by adding w and pu...

Ngày tải lên: 20/02/2014, 18:20

8 440 0
Tài liệu Báo cáo khoa học: "Combining Functionality and Object Orientedness for Natural Language Processing" ppt

Tài liệu Báo cáo khoa học: "Combining Functionality and Object Orientedness for Natural Language Processing" ppt

... descendants, say z and y, a PAL expression for the phrase is one of the following forms: <z>( <V>) or <p>( <z>) where ~a> stands for a PAL expression for a phrase ~*. ... composite expressions are constructed only with a binary form of function application. Thus, if z and I/ are well-formed formulas of PAL, so is a form z(y). Expressions of PAL ar...

Ngày tải lên: 21/02/2014, 20:20

4 422 0
Tài liệu Báo cáo khoa học: "Integrating Symbolic and Statistical Representations: The Lexicon Pragmatics Interface" pot

Tài liệu Báo cáo khoa học: "Integrating Symbolic and Statistical Representations: The Lexicon Pragmatics Interface" pot

... of word senses asso- ciated with word forms. In contrast, the weights that guide abduction correspond to a wider variety of information, and do not necessarily correspond to word sense/form ... We describe a formal framework for inter- pretation of words and compounds in a discourse context which integrates a sym- bolic lexicon/grammar, word- sense proba- bilities, and...

Ngày tải lên: 22/02/2014, 03:20

8 318 0
Báo cáo khoa học: GTP binding and hydrolysis kinetics of human septin 2 pot

Báo cáo khoa học: GTP binding and hydrolysis kinetics of human septin 2 pot

... guanine nucleotides with a K d of 0.28 lm for GTPcS and 1.75 lm for GDP. It has a slow exchange rate of 7 · 10 )5 s )1 for GTPcS and 5 · 10 )4 s )1 for GDP, and an apparent k cat value of 2.7 · 10 )4 s )1 , ... higher K d value of 2.5 lm for GTPcS and 4.4 lm for GDP (Table 1). This was very similar to the values obtained for SEPT2 produced in E. coli (1.7 lm for GTP c...

Ngày tải lên: 07/03/2014, 12:20

13 469 0
Báo cáo khoa học: "Automatic Detection and Correction of Errors in Dependency Treebanks" potx

Báo cáo khoa học: "Automatic Detection and Correction of Errors in Dependency Treebanks" potx

... de- tection. Therefore we have performed the follow- ing experiment: We have counted the numbers of occurrences for the dependencies B  A (the word B is the head of the word A) and C  A (the word C ... simultaneously is very small and therefore these cases are the most likely candidates when looking for errors. 5 Automatic Correction of Errors In this section we propose o...

Ngày tải lên: 07/03/2014, 22:20

5 376 0
Báo cáo khoa học: "Joint Processing and Discriminative Training for Letter-to-Phoneme Conversion" ppt

Báo cáo khoa học: "Joint Processing and Discriminative Training for Letter-to-Phoneme Conversion" ppt

... straightforward. For ex- ample, consider the word “phoenix” and its corre- sponding phoneme sequence [f i n I k s], where we encounter cases of two letters generating a sin- gle phoneme (ph→f), and ... (Daelemans and Bosch, 1997; Black et al., 1998) or instance-based learn- ing (Bosch and Daelemans, 1998). These systems predict a phoneme for each input letter, using the letter...

Ngày tải lên: 08/03/2014, 01:20

9 410 0
Báo cáo khoa học: "Using lexical and relational similarity to classify semantic relations" pptx

Báo cáo khoa học: "Using lexical and relational similarity to classify semantic relations" pptx

... com- bines information about two distinct types of word pair similarity: lexical similarity and relational similarity. We present an efficient and flexible technique for imple- menting relational similarity ... model of pair similarity is based on standard methods for computing semantic similar- ity between individual words. According to this lexical similarity model, word...

Ngày tải lên: 08/03/2014, 21:20

9 416 0
Tài liệu Báo cáo khoa học: "A Best-First Search Algorithm for Generating Referring Expressions" pot

Tài liệu Báo cáo khoa học: "A Best-First Search Algorithm for Generating Referring Expressions" pot

... contribution to exclude potential distractors, as demonstrated by Gardent (2002) — see the examples with objects and descriptors as given in Figures 1 and 2. In the first example, xi and x2 are the ... as dominance and value cut- offs. A dominance cut-off is carried out locally for sibling nodes, when two partial descriptions exclude the same set of potential distractors, a...

Ngày tải lên: 22/02/2014, 02:20

4 672 3
Từ khóa:
w