Báo cáo khoa học: "Unsupervised Multilingual Learning for Morphological Segmentation" potx

... 737–745, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Unsupervised Multilingual Learning for Morphological Segmentation Benjamin Snyder and Regina Barzilay Computer ... lan- guages. 3 Multilingual Morphological Segmentation The underlying assumption of our work is that struc- tural commonality across different languages is a powerful source o...

Ngày tải lên: 31/03/2014, 00:20

... approach is to transform the abbreviation 425 into its full-form for which the current SMT system knows how to translate. For example, if the baseline system knows that the translation for “ ” is “Hong ... Performance 4.5.1 Precision on Translations of Chinese Full-form Phrases For the relations manually tagged as correct in Section 4.4, we manually look at the top-5 transla- tion...

Ngày tải lên: 20/02/2014, 09:20

... Association for Computational Linguistics Unsupervised Topic Modelling for Multi-Party Spoken Discourse Matthew Purver CSLI Stanford University Stanford, CA 94305, USA mpurver@stanford.edu Konrad ... desired general level of granularity. For each set of annotations, we therefore performed two sets of segmentations: one in which the threshold was set for each meeting to give the known...

Ngày tải lên: 20/02/2014, 11:21

... hetero- geneous transfer learning relates to other types of learning, Figure 1 presents an intuitive illustration of four learning strategies, including traditional machine learning, transfer learning across ... in Transfer Learning In the past, several other works made use of trans- fer learning for cross-feature-space learning. Wu and Oard (2008) proposed to handle the cross-...

Ngày tải lên: 08/03/2014, 00:20

Ngày tải lên: 08/03/2014, 01:20

Ngày tải lên: 08/03/2014, 01:20

... Greece, 2 April 2009. c 2009 Association for Computational Linguistics Structural Correspondence Learning for Parse Disambiguation Barbara Plank Alfa-informatica University of Groningen, The Netherlands b.plank@rug.nl Abstract The ... of Structural Correspondence Learning (SCL) (Blitzer et al., 2006) for domain adaptation of a stochastic attribute-value grammar (SAVG). So far, SCL...

Ngày tải lên: 08/03/2014, 21:20

... construc- tion. For instance, one can add λ δ g I (δ, x, i) and λ ′ δ, ˆ δ g ′ I (δ, ˆ δ, x, i) to Equation (1) for δ ∈ {0, 1, , 9}, in order to allow more individualized learning for each label. Notice ... g ′ O are feature vectors defined for Opinion extraction, g P and g ′ P are feature vectors defined for Polarity extraction, and g S and g ′ S are feature vectors defined for St...

Ngày tải lên: 17/03/2014, 00:20

... improve pars- ing performance on monolingual test data for each language by using unsupervised bilingual cues at training time. Multilingual learning has been suc- cessful for other linguistic ... pseudo- counts of 1,000 for negative values and zero, and pseudo-counts of 1,000,000 for positive scores. For Gz node we gave a pseudo-count of 1,000,000 for a score of zero, and 1,0...

Ngày tải lên: 17/03/2014, 01:20

... data. Finally we compared our co-training perfor- mance with supervised learning. For supervised learning, all labeled utterances except for the test set are used for training. We used most confi- dent ... co-training is how to select informative samples. Active learning ap- proaches, such as Muslea et al. (2000), can gener- ally select more informative samples, for example, sample...

Ngày tải lên: 23/03/2014, 16:21