Báo cáo khoa học: "Automatic Story Segmentation using a Bayesian Decision Framework for Statistical Models of Lexical Chain Features" pdf

... distri- bution for lexical chain starts and ends at story boundaries, the uniform distribution for lexical chain start / end at non -story boundary, and the normal distribution for lexical chain continua- tions. ... Modeling of Lexical Chain Features 4.1 Chain starts and ends We follow (Chan et al. 2007) to model the lexi- cal chain starts and ends at a s...

Ngày tải lên: 23/03/2014, 17:20

... Linear Text Segmentation using a Dynamic Programming Algorithm Athanasios Kehagias Dept. of Math., Phys. and Comp. Sciences Aristotle Univ of Thessaloniki GREECE kehagias@egnatia.ee.auth.gr Fragkou ... (Heinonen, 1998) and Utiyama and Isahara (Utiyama and Isa- hara, 2001). Finally, other researchers use probabilistic ap- proaches to text segmentation including the use of hidden...

Ngày tải lên: 31/03/2014, 20:20

... is a nominated list of head- lines of a length of 10 words. In the case of a para- graph of a length less than 10, there will be only one nominated headline of the same length of that paragraph. ... the cate- gory of short summaries. 3 Preparing Data The dataset used in this work was extracted from Arabic Gigaword (Graff, 2007). The Arabic Giga- word is a collec...

Ngày tải lên: 20/02/2014, 05:20

... verse, San: n ¯ aradam paripapraccha v ¯ alm ¯ ıkirmunipu ˙ ngavam gloss: to the Narada asked Valmiki- to the wisest among sages Eng: Valmiki asked the Narada, the wisest among the sages. In the above ... vacah . . We assume that the sandhi handler handling the sandhi involving spaces is available and it splits the above string as, ´ srutv ¯ a caitattrilokaj ˜ nah . v ¯ alm ¯ ıkern ¯ aradah...

Ngày tải lên: 07/03/2014, 22:20

... have large and diverse datasets both for training and evaluation. In this work, we aim to relieve the data acquisition bottleneck associated with automatic image annota- tion by taking advantage ... Mirella Lapata School of Informatics, University of Edinburgh 2 Buccleuch Place, Edinburgh EH8 9LW, UK Y.Feng-4@sms.ed.ac.uk, mlap@inf.ed.ac.uk Abstract The availability of databases of...

Ngày tải lên: 31/03/2014, 00:20

... .158] 4 All raw and normalized corpus data are available from the authors. Table 1: Accuracy of the Verb Clustering Task. Features Accuracy 1. VBD ACT INTI~ CAUS 52% "2. VBD ACT CAUS 54% ... accuracy and standard error. This procedure is then repeated for 10 different ran- dom divisions of the data, and accuracy and standard error are again averaged across the ten runs. e...

Ngày tải lên: 31/03/2014, 21:20

... the head ‘rescue’, and lemma:failing arg:ARG1 var:bank which indicates that the argument of ‘failing’ is ‘bank’. Note that any tree can be transformed into a feature for a particular lexical item ... (The pattern-based approach uses a set of manually- constructed patterns applied to a web search.) In the same vein, Geffet and Dagan (2005) fil- ter the result of a pattern-ba...

Ngày tải lên: 08/03/2014, 21:20

... varies from 50 to 500 at intervals of 50) are checked in each case for grammatical well-formedness and for lexicalization. By lexi- calization we mean the quality of a pair to con- stitute (part ... Its author had to simulate parsing because of the lack, at the time, of parsing tools for Ger- man. Our report, that concerns an actual system and a large data set, validates Bre...

Ngày tải lên: 17/03/2014, 04:20

... is labeled for each particular verb as so-called frames. Addition- ally, semantic roles can also be labeled with one of 13 ARGM adjunct labels, such as ARGM-LOC or ARGM-TMP for additional locational ... solutions are compli- cated, consist of several stages and hand- built features, and are too slow to be applied as part of real applications that require such semantic labels, partly...

Ngày tải lên: 17/03/2014, 04:20

... of the 43rd Annual Meeting of the ACL, pages 346–353, Ann Arbor, June 2005. c 2005 Association for Computational Linguistics Learning Stochastic OT Grammars: A Bayesian approach using Data Augmentation ... contains all the information needed for linguists’ use: for exam- ple, if there is a grammar that will generate the exact frequencies as in the data, such a grammar wil...

Ngày tải lên: 23/03/2014, 19:20