automatic software architecture recovery a machine learning approach

Ngày tải lên: 31/03/2014, 04:20

... class of the antecedent distance in markables between anaphor and antecedent (1 20) same agreement of anaphor and antecedent? same grammatical role of anaphor and antecedent? same semantic class ... classi- ana agr ana semclass* ante npform ante gramrole ante agr ante semclass* dist same agr same gramrole same semclass* and antecedent - NP form, grammatical role, semantic class - are extracted ... 40th Annual Meeting of the Association for Computational Linguistics (ACL’02), pages 104–111, Philadelphia, PA, USA J Ross Quinlan 1993 C4.5: Programs for Machine Learning Morgan Kaufman, San Mateo,...

Ngày tải lên: 17/03/2014, 06:20

... ana npform form of anaphor person, gender, number ana agree grammatical case of anaphor ana case the level of embedding in a sentence ana s depth Coreference-level features compatibility in agreement ... of antecedent ante npform person, gender, number ante agree ante case grammatical case of antecedent the level of embedding in a sentence ante s depth grammatical function of anaphor ana gram ... the markable The feature ante ic (24) as an alternative to ante tfidf is based on the same assumptions as the former The information content of a non-NP-markable is calculated as follows, based...

Ngày tải lên: 23/03/2014, 19:20

... depth: WH cat: WTI lea: join cat: mother cat: daughter catl: daughter cat2: daughter cat3: daughter cat4: daughter cat5: daughter cat6: - daughter cat7: GAP-3 WHADVP why SBARQ VP VB SBAR SBAR UNDEFINED ... success as an indication of the feasibility of our data-driven, modular approach Additionally, our approach has the advantage of wide coverage Since it does not require an extensive lexicon, and ... cat: WIT lex: join cat: mother cat: daughter call: daughter cat2: daughter cat3: daughter cat4: daughter cat5: daughter cat6: daughter cat7: Table 1: Test-set performance of network Percentage...

Ngày tải lên: 24/03/2014, 03:20

Ngày tải lên: 31/03/2014, 20:20

Ngày tải lên: 21/06/2014, 08:20

... Michael Gamon, and Chris Brockett 2001 A machine learning approach to the automatic evaluation of machine translation In Proceedings of the 39th Annual Meeting of the Association for Computational ... show that they are also informative in developing better metrics MT Evaluation with Machine Learning A good automatic evaluation metric can be seen as a computational model that captures a human’s ... in the training set (by languages and by years), and their correlations with human assessment are higher than standard automatic evaluation metrics MT Evaluation Recent automatic evaluation metrics...

Ngày tải lên: 08/03/2014, 02:21

... formalization of similarity-based approach would be essential, as pattern-based approach is enhanced with the supervised machine learning In this paper, we propose a novel approach to automatic ... Dekang Lin 1998 Automatic retrieval and clustering of similar words Proc of COLING/ACL 98, 786–774 Shachar Mirkin, Ido Dagan, and Maayan Geffet 2006 Integrating pattern-based and distributional ... syntactic pattern clues even more difficult The reason of the drastic improvement is that, as far as we speculate, the supervised learning may have favorably worked to cause the same effect as automatic...

Ngày tải lên: 23/03/2014, 17:20

... of AAAI/IAAI’00, pages 703–710 I Langkilde 2000 Forest-Based Statistical Sentence Generation In Proc of NAACL’00, pages 170–177 C Lin 2004 ROUGE: A Package for Automatic Evaluation of Summaries ... where an aliased application does not actually reside a file or application statement provides a visible icon in folders where an aliased application does not actually reside the user can transmission ... path statement provides a visible icon in folders where an aliased application does not actually reside a file or application alias provides a visible icon in folders where an aliased application...

Ngày tải lên: 20/02/2014, 12:20

... Liang Huang, and Qun Liu 2009 Automatic Adaptation of Annotation Standards: Chinese Word Segmentation and POS Tagging - A Case Study In Proceedings of ACL 2009, pages 522-530 Wenbin Jiang and ... Romain Thibaux, and Dan Klein 2006 Learning Accurate, Compact, and Interpretable Tree Annotation In Proceedings of ACL 2006, pages 433-440 Slav Petrov, Pi-Chuan Chang, Michael Ringgaard, and ... heterogeneous parser, we use feature-based parsing algorithms in order to easily incorporate features that encode source-side bracketing structures Theoretically, any featurebased approaches are applicable,...

Ngày tải lên: 17/03/2014, 00:20

... Grammatical Feature SOON STR # Feature Type Lexical Table 1: Feature Set for the Duplicated Soon Baseline system The feature set contains relational and non-relational features Non-relational ... features, on the other hand, has 86 leaves with an average of 322 instances per leaf Hand-selected feature sets As a result, we next evaluate a version of the system that employs manual feature ... work was supported in part by DARPA TIDES contract N66001-00-C-8009, and NSF Grants 0081334 and 0074896 References C Aone and S W Bennett 1995 Evaluating Automated and Manual Acquisition of Anaphora...

Ngày tải lên: 17/03/2014, 08:20

... findings at the collegewide research symposium, and sometimes they also present papers at the national conference such as American Association of Health, Physical Education, Recreation, and Dance (AAHPERD) ... health education programs and evaluating such programs after they have ended are important, health agencies lack enough professionals that are prepared to these tasks; therefore, health agencies ... colleges and universities need to advocate and adopt such policies and make service -learning an integral part of higher education The collaboration between all parties can eventually enhance community-based...

Ngày tải lên: 22/03/2014, 15:21

Ngày tải lên: 30/03/2014, 17:20

Ngày tải lên: 08/04/2014, 12:44

Ngày tải lên: 11/09/2015, 09:10

Ngày tải lên: 12/09/2015, 08:20

Ngày tải lên: 15/09/2015, 17:10

Ngày tải lên: 09/10/2015, 11:24

... integrated into a phrasebased decoder serving as additional distortion features We evaluated our approach on large-scale Japanese-English and English-Japanese machine translation tasks, and experimental ... Ramanathan, Pushpak Bhattacharyya, Jayprasad Hegde, Ritesh M Shah and Sasikumar M 2008 Simple syntactic and morphological processing can help English-Hindi Statistical Machine Translation In ... Search and Learning for the Linear Ordering Problem with an Application to Machine Translation Ph.D Thesis Karthik Visweswariah, Jiri Navratil, Jeffrey Sorensen, Vijil Chenthamarakshan and Nandakishore...

Ngày tải lên: 19/02/2014, 19:20