Báo cáo khoa học: "Word Association Norms, Mutual Information, and Lexicography" pot

Báo cáo khoa học: "Word Association Norms, Mutual Information, and Lexicography" pot

Báo cáo khoa học: "Word Association Norms, Mutual Information, and Lexicography" pot

... Word Association Norms, Mutual Information, and Lexicography Kenneth Ward Church Bell Laboratories Murray Hill, N.J. Patrick Hanks CoLlins Publishers Glasgow, Scotland Abstract ... corpora. (The standard method of obtaining word association norms, testing a few thousand subjects on a few hundred words, is both costly and unreliable.) The , proposed measure, the ass...

Ngày tải lên: 24/03/2014, 02:20

8 167 0
Báo cáo khoa học: "Word Association and MI-Trigger-based Language Modeling" potx

Báo cáo khoa học: "Word Association and MI-Trigger-based Language Modeling" potx

... word pair was stronger and faster than that to a poorly associated word pair. The strength of word association can be measured by mutual information. By computing mutual information of a ... windows size and i- j + 1 is the distance between the words w. and w i . The first item in each of Equation 5 and 6 is the logarithmic probability of S using a word unigram model and...

Ngày tải lên: 23/03/2014, 19:20

7 332 0
Báo cáo khoa học: "Word Sense Induction for Novel Sense Detection" pot

Báo cáo khoa học: "Word Sense Induction for Novel Sense Detection" pot

... the work of Brody and Lapata (2009) and others, we approach WSI via topic modelling — using La- tent Dirichlet Allocation (LDA: Blei et al. (2003)) and derivative approaches — and use the topic model ... (Agirre and Soroa, 2007), so we similarly apply our HDP method to this dataset for direct comparability. In the remainder of this section, we refer to Brody and Lapata (2009) as B...

Ngày tải lên: 17/03/2014, 22:20

11 285 0
Báo cáo khoa học: "Word Sense Disambiguation Improves Information Retrieval" ppt

Báo cáo khoa học: "Word Sense Disambiguation Improves Information Retrieval" ppt

... disambiguate terms in both queries and documents with the senses pre- defined in hand-crafted sense inventories, and then used the senses to perform indexing and retrieval. Voorhees (1993) used ... (1) where p(t|θ q ) and p(t|θ d ) are the generative proba- bilities of a term t from the models θ q and θ d , V is the vocabulary of C, and E(θ q ) is the entropy of q. Define tf (t, d)...

Ngày tải lên: 23/03/2014, 14:20

10 335 0
Báo cáo khoa học: "Word Alignment via Submodular Maximization over Matroids" pot

Báo cáo khoa học: "Word Alignment via Submodular Maximization over Matroids" pot

... Bilmes, 2004; Narasimhan and Bilmes, 2005; Krause and Guestrin, 2005; Narasimhan and Bilmes, 2007; Krause et al., 2008; Kolmogorov and Zabin, 2004; Jegelka and Bilmes, 2011) and have recently been ... and Pedersen, 2003). This corpus con- sists of 1.1M automatically aligned sentences, and comes with a test set of 447 sentences, which have been hand-aligned and are marked wit...

Ngày tải lên: 23/03/2014, 16:20

6 187 0
Tài liệu Báo cáo khoa học: "TRANSPORTABLE NATURAL-LANGUAGE INTERFACES: PROBLEMS AND TECHNIQUES" pot

Tài liệu Báo cáo khoa học: "TRANSPORTABLE NATURAL-LANGUAGE INTERFACES: PROBLEMS AND TECHNIQUES" pot

... as simplifying the general problem and where, on the other hand, transportability (and the way in which database systems typically structure information and view the world) makes things ... schema and the database schema, these must be organized so that the information they encode about any particular database and its corresponding domain can be obtained systematically (a...

Ngày tải lên: 21/02/2014, 20:20

5 375 0
Tài liệu Báo cáo khoa học: "A COMMON FRAMEWORK FOR ANALYSIS AND GENERATION" potx

Tài liệu Báo cáo khoa học: "A COMMON FRAMEWORK FOR ANALYSIS AND GENERATION" potx

... analysis and generation. We argue that the only part of the average NL system's knowledge that we can have any faith in is its vocabulary and, to a lesser ex- tent, its syntactic rules, and ... from the discourse representations of the subject and the predicate. The subject and predicate each pro- vide some background constraints, and then their meanings get combined (...

Ngày tải lên: 22/02/2014, 10:20

4 502 0
Báo cáo khoa học: "Lexical Disambiguation: Sources of Information and their Statistical Realization" docx

Báo cáo khoa học: "Lexical Disambiguation: Sources of Information and their Statistical Realization" docx

... understanding of the text or frequency characteristics of it. One kind of information relates to the under- standing of the meaning of the text, using semantic and pragmatic knowledge and applying ... the relative frequencies of word senses and associations between word senses. These fac- tors were shown to play an important role in lexical retrieval, and were suggested as releva...

Ngày tải lên: 17/03/2014, 08:20

2 243 0
Báo cáo khoa học: "A Model of Lexical Attraction and Repulsion*" potx

Báo cáo khoa học: "A Model of Lexical Attraction and Repulsion*" potx

... Nikkei corpus, and the Switchboard corpus of conversational speech. Upper row: All non-self (left) and self triggers (middle) appearing fewer than 100 times in the Nikkei corpus, and the curve ... (middle), and all self triggers appearing fewer than 100 times in the entire Switchboard corpus (right). the distribution p, has mean 1/y and variance 1/y 2. This distribution is a go...

Ngày tải lên: 24/03/2014, 03:21

8 291 0
Báo cáo khoa học: "A Calculus for Semantic Composition and Scoping" pot

Báo cáo khoa học: "A Calculus for Semantic Composition and Scoping" pot

... (Curry and Feys, 1968; Stenlund, 1972; Anderson and Be]nap, 1975). In contrast, with the restriction we have the weaker system of pure rel- evant implication R- (Prawitz, 1965; Anderson and Bel- ... Dordrecht, Netherlands. Haskell B. Curry and Robert Feys. 1968. Com- binatory Logic, Volume L Studies in Logic and the Foundations of Mathematics. North- Holland, Amsterdam, Holla...

Ngày tải lên: 31/03/2014, 18:20

9 285 0
w