Báo cáo khoa học: "Learning from evolving data streams: online triage of bug reports" potx
... Linguistics Learning from evolving data streams: online triage of bug reports Grzegorz Chrupala Spoken Language Systems Saarland University gchrupala@lsv.uni-saarland.de Abstract Open issue trackers are a type of ... the effectiveness of online learning algorithms by evaluating them on several bug report datasets collected from open issue trackers associated with lar...
Ngày tải lên: 24/03/2014, 03:20
... classifier with robustness from noisy data (Ko and Seo, 2004). How can labeled training data be automatically created from unlabeled data and title words? Maybe unlabeled data don’t have any information ... slide from the first word of the document to the last in the size of the window (60 words) and the interval of each window (30 words). Therefore, the final outp...
Ngày tải lên: 20/02/2014, 16:20
... mathematical theory of evo- lution, based on the conclusions of dr. j. c. willis, f.r.s. Philosophical Transactions of the Royal Society of London. Series B, Containing Papers of a Biological Character, ... Conference of the North American Chapter of the Association for Com- putational Linguistics; Proceedings of the Main Con- ference, pages 97–104. 1108 Proceedings of the 4...
Ngày tải lên: 30/03/2014, 21:20
Báo cáo khoa học: "Learning Constraint Grammar-style disambiguation rules using Inductive Logic Programming" potx
... consisted of the tags of all of the words on each side of the word to be disambiguated (the target word). Given no unknown words and a tag set of 43 different tags, the system tagged 96.4% of the ... and part of speech tag along with a set of morphological features (if any). A different set of training data was produced for each of the 24 part speech categories. T...
Ngày tải lên: 17/03/2014, 07:20
Báo cáo khoa học: "Learning Predictive Structures for Semantic Role Labeling of NomBank" pptx
... combined, we use the first 100 prob- lems from each of the six groups of observable aux- iliary problems. In selected combined, we use the first 100 problems from each of path, chunkseq, last- word and ... m ma- trix. The first h columns of V 1 are stored as rows of Θ. 4. Given Θ, we learn w and v for each of the k target problems by minimizing the empirical risk of the associa...
Ngày tải lên: 23/03/2014, 18:20
Báo cáo khoa học: "Multiple Interpreters in a Principle-Based Model of Sentence Processing" potx
... specification of a program from its execution. A program specification consists of a set of axioms from which solution(s) can be proved as de- rived theorems. Within this paradigm, the nature of computation ... propose consists of a num- ber of processors over subsets of the grammar. Cen- tral to the model is a declarative specification of the principles of grammar...
Ngày tải lên: 18/03/2014, 02:20
Báo cáo khoa học: "Learning Condensed Feature Representations from Large Unsupervised Data Sets for Supervised Learning" docx
... amount of unsupervised data to supplement supervised data. Specifically, an approach that involves incorporating ‘clustering- based word representations (CWR)’ induced from unsupervised data as ... and used in place of F in supervised learning. The largest contribution of our method is that it offers an architecture that can drastically reduce the number of features, i.e., from...
Ngày tải lên: 07/03/2014, 22:20
Báo cáo khoa học: "Learning the Countability of English Nouns from Corpus Data" ppt
... in the ALT-J/E data, so this class was hand- checked, giving a total of 104 entries; 84 of these were attested in the training data. Our classification of countability is a subset of ALT-J/E’s, ... chose this be- cause of its good coverage of different usages of En- glish, and thus of different countabilities. The only component of the original annotation we make use of...
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "Learning Effective Multimodal Dialogue Strategies from Wizard-of-Oz data: Bootstrapping and Evaluation" pot
... with a simulated envi- ronment which is “bootstrapped” from small amounts of Wizard -of- Oz (WOZ) data. This use of WOZ data allows development of op- timal strategies for domains where no work- ing ... Barto, 1998), where the simulated environment is learned from small amounts of Wizard -of- Oz (WOZ) data. Us- ing WOZ data rather than data from real Human- Computer Inte...
Ngày tải lên: 23/03/2014, 17:20
Báo cáo khoa học: "Learning Phrase-Based Spelling Error Models from Clickthrough Data" pot
... with this same data with the hope of achieving similar improvements in our task. The data consist of a set of query sessions that were extracted from one year of log files from a commercial ... report results using this dataset. The clickthrough data of the second type con- sists of a set of query reformulation sessions extracted from 3 months of log files fr...
Ngày tải lên: 30/03/2014, 21:20