Báo cáo khoa học: "Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates" doc

... Improving Pronoun Resolution by Incorporating Coreferential Information of Candidates Xiaofeng Yang †‡ Jian Su † Guodong Zhou † Chew Lim Tan ‡ † Institute ... Finally, conclusion is given in Sec- tion 7. 2 The Impact of Coreferential Information on Pronoun Resolution In pronoun resolution, the center of attention throughout the discourse segment is a very ... the...

Ngày tải lên: 31/03/2014, 03:20

... improve the resolution of neutral pronouns. 1 Introduction Semantic compatibility is an important factor for pronoun resolution. Since pronouns, especially neu- tral pronouns, carry little semantics of ... effectiveness of the semantic feature on different types of pronouns, the whole resolution was divided into neutral pronoun (it & they) reso- lution and personal prono...

Ngày tải lên: 20/02/2014, 15:20

... context of the ACE Information Extraction evaluations, and we will use the terminology of these evaluations: entity: an object or a set of objects in one of the semantic categories of interest ... hypotheses and have them re-ranked by subsequent stages of processing. We obtained thereby a reduction of 24% in spurious and incorrect name tags, and a reduction of 14%...

Ngày tải lên: 23/03/2014, 19:20

... of coreferential pronoun (2) Identification of antecedent head (3) English – Czech mapping of antecedent head (4) Extraction of number and gender of Czech word (5) Annotation of English pronoun ... any Czech pronoun. 6. Total coreferential English pronouns trans- lated as a Czech pronoun corresponding to a valid translation of the English pronoun. 7. Total coref...

Ngày tải lên: 17/03/2014, 22:20

... Recommendation by Exploiting Information Need Shuguang Li Department of Computer Science University of York, YO10 5DD, UK sgli@cs.york.ac.uk Suresh Manandhar Department of Computer Science University of ... Information Need Prediction After estimating the statistical translation probabili- ties, we treat the information need prediction as the process of ranking words by p(...

Ngày tải lên: 23/03/2014, 16:20

... as one of its inputs, as shown by the link from QP in QS1 to CM. This inverted QFrame can be generated by a set of simple transformations, substituting the pivot term in the bag of words ... across other collections, as long as the size of the set of second-place answers is at least about 1/10 of the set of first-place answers, this form of the Constraint process can...

Ngày tải lên: 23/03/2014, 18:20

... There were 71 pronouns in the 140 page technical manual; 7 of the pronouns were non-anaphoric and 16 exophoric. The resolution of anaphors was carried out with a suc- cess rate of 95.8%. The ... knowl- edge-poor approach to pronoun resolution which does not parse and analyse the input in order to identify antecedents of anaphors. It makes use of only a part -of- speech...

Ngày tải lên: 31/03/2014, 04:20

... history in a straightforward way. This idea of converting full parsing into a se- ries of chunking tasks is not new by any means— the history of this kind of approach dates back to 1950s (Joshi and ... the product of the probabilities output by the individual CRF chunkers: score = h  i=0 p(y i |x i ), (1) where i is the level of chunking and h is the height of the tree. The...

Ngày tải lên: 17/03/2014, 22:20

... mode of action of RMI1 in the regulation of energy homeostasis might be based on the regulation of adipocyte hyperplasia. Studies have shown that siRNA knockdown of RMI1 resulted in suppression of ... cause of adult obesity, and hyperplasia of adipocytes in obese adults some- times occurs secondary to adipocyte hypertrophy, pos- sibly due to an increased number of adipocytes...

Ngày tải lên: 06/03/2014, 01:20

... degree of document similarity for each pair of documents. Then we represent the collection as a graph. Definition: A labeled graph is called graph of collection if where and each edge is labeled by number ... parameter. This feature of the GRA has been designed for the sake of generalization, in order to not overfit the input sample. The input of the GRA consists of (i) a sam- p...

Ngày tải lên: 08/03/2014, 04:22