Tài liệu Báo cáo khoa học: "Learning Word-Class Lattices for Definition and Hypernym Extraction" doc

... grammatical and pro- cessing framework for handling the repairs, hesitations, and other interruptions in nat- ural human dialog. The proposed frame- work has proved adequate for a collection ... (urn) and speech re- pairs (I mean) and give meta-comments on the ut- terance (right). specify how speech repairs should be handled by the parser. (Hindle, 1983) and (Bear et al...

Ngày tải lên: 20/02/2014, 19:20

... Association for Computational Linguistics, pages 1318–1327, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Learning Word-Class Lattices for Definition and Hypernym ... a term to its hypernym, and a dependency parser is used to represent them. 3 Word-Class Lattices 3.1 Preliminaries Notion of definition. In our work, we rely on a forma...

Ngày tải lên: 20/02/2014, 04:20

... s k is the sentiment label for document d k , we wish to maximize the probability of document labels given the documents. We assume documents in the collec- tion and words within a document are i.i.d. ... is done for each document class and then one value is subtracted from the other. Martineau and Finin present evidence that this weighting helps with sen- timent classification, and...

Ngày tải lên: 20/02/2014, 04:20

... (Pantel and Lin, 2002; Sch¨utze, 1998), there are other related efforts on word sense discrimination (Dorow and Widdows, 2003; Fukumoto and Suzuki, 1999; Pedersen and Bruce, 1997). In (Pedersen and ... be distinguished using only bag-of-words information, and their difference lies in syntactic information held by features. For example, the third sense and the sixth sense of “i...

Ngày tải lên: 20/02/2014, 16:20

... Improved Parser for Data-Oriented Lexical-Functional Analysis Rens Bod Informatics Research Institute, University of Leeds, Leeds LS2 9JT, UK, & Institute for Logic, Language and Computation, ... frag- ment size is confirmed for LFG-DOP; (3) LFG- DOP's relative frequency estimator performs worse than a discounted frequency estimator; and (4) LFG-DOP significantly outperform...

Ngày tải lên: 20/02/2014, 18:20

... (0.7,0.6), because for metric1: 0.7 > 0.6 and for metric2: 0.6 > 0.4. There is another definition of optimality, which disregards ties and may be easier to visualize: Definition 2. Weakly ... p 1 = [0, 1] and p 2 = 1 − p 1 and recording the set of hypotheses that maximizes  k p k M k (h). For 0.6 < p 1 ≤ 1 we get h = (0.9, 0.1), for p 1 = 0.6 we get (0.7, 0.6), an...

Ngày tải lên: 19/02/2014, 19:20

... SCFs) and a mapping from surface frames to the underlying predicate-argument structure. In- formation about verb subcategorization is useful for tasks like information extraction (Cohen and Hunter, 2006; ... manual effort, and higher coverage and scalability. Unfortunately, high quality SCF lexicons are dif- ficult to build automatically. The argument-adjunct distinction is challengi...

Ngày tải lên: 19/02/2014, 19:20

... engine, and automatically annotating the snippets with tags and features for training a conditional random field model. At run- time, the model is used to extracting translation candidates for ... data for a machine translation system, as described in Lin et al. (2008). 2 Related Work Phrase translation and transliteration is important for cross-language tasks. For examp...

Ngày tải lên: 19/02/2014, 19:20

... of noun-noun and verb-verb pairs (Sinha and Mihalcea, 2007; Guo and Diab, 2010). Our similarity measure wmfvec exploits the same information (sense defini- tions) elesk and ldavec use, and outperforms ... the best of them and com- bine them into one system. Specifically, in their im- plementation they use jcn for noun-noun and verb- verb pairs, and elesk for other pairs. (Si...

Ngày tải lên: 19/02/2014, 19:20

... order in which we visit landmarks and the side we pass them on. To determine the order P e visits landmarks we compute the minimum distance from P e to each landmark, and threshold it at a fixed ... first author and award IIS-0811974 to the second author and by the Air Force Research Laboratory (AFRL), under prime contract no. FA8750-09-C-0181. Thanks to Michael Levit and Deb Roy for...

Ngày tải lên: 20/02/2014, 04:20