Báo cáo khoa học: "Text Segmentation with Multiple Surface Linguistic Cues" pptx

... overall measure to rank the possible segmentation with multiple linguistic cues. First we explain this method used for text seg- mentation with multiple linguistic cues. Here, we represent ... Combining multiple surface cues is effective for text segmentation. • The multiple regression analysis with the step- wise method is good for selecting the useful cues for...

Ngày tải lên: 31/03/2014, 04:20

... pages 269–272, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Text Segmentation with LDA-Based Fisher Kernel Qi Sun, Runxin Li, Dingsheng Luo and Xihong Wu Speech ... similarity by the Fisher kernel. Finally global best segmentation is achieved by dynamic programming. Experi- ments on Chinese data sets with the technique show it can be effective. Int...

Ngày tải lên: 23/03/2014, 17:20

... TEXT UNDERSTANDING WITH MULTIPLE KNOWLEDGE SOURCES: AN EXPERIMENT IN DISTRIBUTED PARSING Cinzia Costantini, Danilo ... activities combine with top-down, expectation-driven ones to cooperatively determine the most I~ely interpretation of the input (Lesgoid and Perfetti, 1981). Roughly speaking, humans begin with a set ... the text. These expectations are based both on linguistic...

Ngày tải lên: 01/04/2014, 00:20

... associating each node with one of the three atomic values ass, rec or 0. These values represent the Case properties of the node they are associated with; a node associated with the property ... Case assigner, a node associated with the property rec must be capable of being assigned Case, and a node associated with the property 0 must be neutral with respect to Case. The Cas...

Ngày tải lên: 17/03/2014, 20:20

... an unknown language without learning data. In other words, we use supervised learning. In line with recent trends in unsupervised segmentation, the problem of finding segments without supervision ... learning methods for languages with abun- dant supervision, and the performance is usually high enough for practical use. This article con- cerns that problem together with segmentation b...

Ngày tải lên: 07/03/2014, 18:20

... Association of Computational Linguistics, pages 840–847, Prague, Czech Republic, June 2007. c 2007 Association for Computational Linguistics Chinese Segmentation with a Word-Based Perceptron ... based on local char- acter features are used to make the tagging decisions, with Viterbi decoding finding the highest scoring segmentation. In this paper we propose an alternative, word-based s...

Ngày tải lên: 08/03/2014, 02:21

... the university events mailing list, sent to people associated with the university, but with no particular linguistic training. Linguistics first-year students and Computer Science students ... 2-7 August 2009. c 2009 ACL and AFNLP Dialogue Segmentation with Large Numbers of Volunteer Internet Annotators T. Daniel Midgley Discipline of Linguistics, School of Computer Science and...

Ngày tải lên: 17/03/2014, 01:20

... rules within one derivation. • As multiple derivations are used for finding optimal translations, we extend the minimum error rate training (MERT) algorithm (Och, 2003) to tune feature weights with ... into an English sentence “give a talk”. ing with multiple models achieves an absolute im- provement of 1.5 BLEU points over individual de- coding with single models (Section 5). 2 Back...

Ngày tải lên: 23/03/2014, 16:21

... 3.83 (83.3%) Table 1. Comparison of segmentation algorithm using different linguistic features. Discussion: The segmentation algorithm using the linguistic features word repetition and ... results demonstrate that supplementing word repetition with other linguistic features can improve text segmentation. As an example, a text segmentation algorithm developed by Hearst...

Ngày tải lên: 31/03/2014, 04:20

... Association for Computational Linguistics, pages 264–269, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Authorship Attribution with Author-aware Topic Models Yanir ... emails with 72 authors (Argamon and Juola, 2011); and (2) Blog: blogs with 19,320 authors (Schler et al., 2006). These datasets represent realistic scenar- ios of AA of user-ge...

Ngày tải lên: 23/03/2014, 14:20