Báo cáo khoa học: "A Class of Submodular Functions for Document Summarization" pot

... 2011. c 2011 Association for Computational Linguistics A Class of Submodular Functions for Document Summarization Hui Lin Dept. of Electrical Engineering University of Washington Seattle, WA ... USA hlin@ee.washington.edu Jeff Bilmes Dept. of Electrical Engineering University of Washington Seattle, WA 98195, USA bilmes@ee.washington.edu Abstract We design a class of...

Ngày tải lên: 23/03/2014, 16:20

... the sparsity of the training data. 3 DualSum 3.1 Model Formulation The input for DUALSUM is a set of pairs of collec- tions of documents C = {(A i , B i )} i=1 m , where A i is a base document collection ... ob- tained. Because of the non-deterministic nature of Gibbs sampling, the results reported here are the average of five runs for all the baselines and for DUALSUM. D...

Ngày tải lên: 31/03/2014, 20:20

... Computing Sciences, University of Sussex Falmer, Brighton BN1 9QH, UK *Center for the Study of Language and Information, Stanford University Ventura Hall, Stanford, CA 94305-4115, USA {kiefer, ... unification. Therefore, any improvements in the efficiency of unification would have direct conse- quences for the overall performance of the sys- tem. One key to reducing the c...

Ngày tải lên: 08/03/2014, 06:20

... sequence of I words f Source sequence of J words a Sequence of K phrase alignments for e, f Π Permutation of the alignments for target word order e h Sequence of M feature functions λ Sequence of ... learned weights for the M features H A priority queue of hypotheses Class- based Agreement Model t ∈ T Set of morpho-syntactic classes s ∈ S Set of all word segments...

Ngày tải lên: 16/03/2014, 19:20

... gen- eration of basic Stanford dependencies (for constituent parsers) and part -of- speech tagging (for dependency parsers). 3 Results Table 3 tabulates efficiency and performance for all parsers; ... Linguistics A Comparison of Chinese Parsers for Stanford Dependencies Wanxiang Che † car@ir.hit.edu.cn Valentin I. Spitkovsky ‡ vals@stanford.edu Ting Liu † tliu@ir.hit.edu.cn † School...

Ngày tải lên: 23/03/2014, 14:20

... BUILDING(s) (of) ONE/ALONE (of) DOUBLE/GEMINATE (of) ANNUAL/YEARS (of) LAYER/LAMELLA (of) (to /for) (by/with/as) LINE (of) THIN-CRUST(s) HOW/AS/BUT (of) (to /for) (by/with/as) FOSSILIZED (of) (to /for) - ... words" for the sake of simplicity. The target equivalents of the single meaning words have different degrees of probability of occurrence in the different fields...

Ngày tải lên: 30/03/2014, 17:20

... the document. From a linguistic point of view, a document is made up of words, and the semantics of the doc- ument is determined by the meaning of the words and the linguistic structure of the document. ... captures the information of which words are used in a document, but not the number of times each words is used, nor the order of the words in the document. In the s...

Ngày tải lên: 31/03/2014, 20:20

... scope of the two quantifiers. Each of these solved forms now stands for a separate class of models; for instance, the first model in Fig. 1 is a model of (7), whereas the second is a model of (8). 3.4 ... of choices for the subsets S  in condition 2 of Def. 7, and there is only a finite set of choices of new dom- inance atoms that satisfy condition 3. Therefore, the se...

Ngày tải lên: 31/03/2014, 20:20

... Abholung are part of the corpus. The same problem also occurs for German nouns. Therefore, this first condition of the affix acqui- sition step needs to be replaced. We therefore intro- duced an ... stable (±1% f-score) for any cutting point on the slope between 20% and 50% of the list (for the German data set ranks 4000 and 12000), but importantly before the function tails off. The...

Ngày tải lên: 17/03/2014, 04:20

... Learning of Dependency Structure for Language Modeling Jianfeng Gao Microsoft Research, Asia 49 Zhichun Road, Haidian District Beijing 100080 China jfgao@microsoft.com Hisami Suzuki Microsoft ... the N-best list of N=100, whose “oracle” CER (i.e., the CER of the hy- potheses with the minimum number of errors) is presented in Table 1, indicating the upper bound on performanc...

Ngày tải lên: 17/03/2014, 06:20