Báo cáo khoa học: "Effective Measures of Domain Similarity for Parsing" pdf

... Association for Computational Linguistics Effective Measures of Domain Similarity for Parsing Barbara Plank University of Groningen The Netherlands b.plank@rug.nl Gertjan van Noord University of Groningen The ... Angeles, California, June. Association for Computational Linguistics. Vincent Van Asch and Walter Daelemans. 2010. Us- ing Domain Similarity for Performance E...

Ngày tải lên: 30/03/2014, 21:20

... appli- cations of schemata. The semantic representation of the new phrase is calculated at the same time. As such, an HPSG parse forest can be considered to be a forest of signs. Making use of these ... subtrees with a height of 7 for c0. Suppose that the input for- est is binarized and that |E| is the average number of hyperedges of each node, then we must generate O(|E| 2...

Ngày tải lên: 30/03/2014, 21:20

... questions, etc. The {topic→information} index requires iden- tification of the topic for each call to make use of information available in the model. Below we show examples of the use of the model for topic identification. 5.1 ... because of its hierarchical nature where information can be obtained for topics of various granularity unlike (Mishne et al., 2005) where there is n...

Ngày tải lên: 31/03/2014, 01:20

... definition of a predicate, we may also change its set of MSEA's. We call the set of MSEA's existing for a current definition of a predi- cate the set of active MSEA's for this ... translate well-formed expression of the source language into expressions of the language of "semantic" representation, such as regularized operator-argument form...

Ngày tải lên: 24/03/2014, 02:20

... preference for one particular metonymy, which is of special inter- est for reporting verbs, namely where the name of a country, of a country's citizens, of a capital, or even of the building ... Pustejovsky and Anick (1990) for a description of tools for such a semi-automatic acquisition of se- mantic information from a large corpus). Using qualia structure as...

Ngày tải lên: 24/03/2014, 05:21

... results. For the questions common for all the annota- tors we capture about 70% of the answers for three out of four domains. After studying the re- sults we noticed that for the earthquake domain some ... input informa- tion about the domain but allowed them to use any sources to learn more information about the do- main. We had ten subjects, each of which created one list...

Ngày tải lên: 17/03/2014, 04:20

... algo- rithms have been implemented for mobile devices, of ce software (Open Of ce Writer), search en- gines (Google query completion), and in special- needs software for writers who have difficulties typing ... neuro- logical issues. Training data for this combi- nation of language (Dutch), text type (FAQ) and domain (medical/neurological) is sparse. Therefore, we search for the...

Ngày tải lên: 17/03/2014, 22:20

... Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading. Association for Computational Linguistics, Los Angeles, Califor- nia, June. Thiago ... Pro- ceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learn- ing by Reading, pages 15–23, Los Angeles, California, June. Association f...

Ngày tải lên: 23/03/2014, 16:20

... results suggest that identification of domain- specific senses (IDSS) may actually be of benefit. 1 Introduction Domain- specific sense of a word is crucial informa- tion for many NLP tasks and their applications, ... motivation for their work was similar to ours, i.e., to try to capture changes in ranking of senses for documents from different do- mains. Domain adaptation is al...

Ngày tải lên: 30/03/2014, 21:20

... tissues and in the plasma of vertebrates (for a review, see [1]). It belongs to a wider group of actin-binding proteins that share a number of repeated domains; six in the case of gelsolin itself, ... Digestion of G4–6 domain by trypsin (trypsin/G4–6 ratio: 1/25 w/w) for 10 min molecular weight markers (lane T). G4–6 domain (46 kDa) before proteolysis (lane 1). G4–6 digest in...

Ngày tải lên: 31/03/2014, 01:20