Báo cáo khoa học: "Fine-grained Genre Classification using Structural Learning Algorithms" doc

... a way of using information on the hierarchy of labels for improving fine-grained genre classification. To the best of our knowl- edge, this is the first work presenting structural genre classification ... of machine learning in genre classification used a list of labels as clas- sification categories. However, genre classes are often organised into hierar- chies, e.g., covering t...

Ngày tải lên: 30/03/2014, 21:20

... France, April 23 - 27 2012. c 2012 Association for Computational Linguistics User Edits Classification Using Document Revision Histories Amit Bronner Informatics Institute University of Amsterdam a.bronner@uva.nl Christof ... automatically distinguishing be- tween factual and fluency edits in document revision histories. The approach is based on supervised machine learning using lan- g...

Ngày tải lên: 22/02/2014, 03:20

... gives experimental analysis. Section 5 concludes the paper. 2 Hierarchical Text Classification In text classification, the documents are often rep- resented with vector space model (VSM) (Salton et al., ... hierarchi- cal classification algorithms. 1 Introduction Text classification is a crucial and well-proven method for organizing the collection of large scale documents. The predefined ca...

Ngày tải lên: 20/02/2014, 05:20

... English POS-tagging using freely-available TnT tagger (Brants, 2000), and lemmatization using wnmorph, included in the WordNet pack- age (Miller et al., 1991). • Spanish POS-tagging using FreeLing ... inflectional nature of the Spanish language. 4.2 Verb Phrase Detection /Classification Table 2 shows the number of detected verbs using the detection rules presented in section 3.1, and t...

Ngày tải lên: 17/03/2014, 06:20

... much too com- plicated for simple multiword expressions, such as (12). 4 Previous Classifications There are numerous classifications available in lin- guistic literature, and we considered three of ... significantly better parsing coverage. 2.2 Semantically Idiosyncratic Expressions The other g roup in our classification consists of multiword expressions that are idiosyncratic from the point of...

Ngày tải lên: 31/03/2014, 01:20

... quantify the problem. We provide a baseline and the results from a first attempt at a discriminative learning pro- cedure for this task, achieving 80% accuracy. 1 Introduction Earlier work on parsing ... provide the first baseline for this problem as well as preliminary results from a dis- criminative learning procedure for the task. 2 The Problem in More Detail As mentioned above, iDAfa co...

Ngày tải lên: 17/03/2014, 02:20

... dependency parsing by using (automatically) translated texts attached with transformed dependency information. As a case study, we consider how to enhance a Chinese dependency parser by using a translated ... 0.858 +d a 0.848 0.860 +T b -d 0.859 0.869 +d 0.861 0.870 a +d: using three Markovian features preact and beam search decoding. b +T: using features derived from the translated t...

Ngày tải lên: 17/03/2014, 01:20

... existing lexicalized parsing models using head-head depen- dencies, while successful for English, fail to outperform an unlexicalized baseline model for German. Learning curves show that this effect ... results of the PP experiment are listed in Ta- ble 5. Again, we give results obtained using TnT tags and using perfect tags. The row ‘Split PP’ contains the performance figures obtained...

Ngày tải lên: 17/03/2014, 06:20

... July 2012. c 2012 Association for Computational Linguistics Semi-supervised Dependency Parsing using Lexical Affinities Seyed Abolghasem Mirroshandel †, Alexis Nasr † Joseph Le Roux  † Laboratoire ... on treebanks composed of few thousands sentences. While this amount of data seems reasonable for learning syn- tactic phenomena and, to some extent, very frequent lexical phenomena involvi...

Ngày tải lên: 30/03/2014, 17:20

... number of weak learners). When using a very short code, the error-correcting CRF will not adequately model the decision bound- aries between all classes. However, using a long code will lead to ... computed using the forward backward algorithm. The decoding proceeds as before, however instead of a bit string we have a vector of probabilities. This vector is compared to each of the label...

Ngày tải lên: 31/03/2014, 03:20