Báo cáo khoa học: "Text-level Discourse Parsing with Rich Linguistic Features" pdf

... for Computational Linguistics, pages 60–68, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Text-level Discourse Parsing with Rich Linguistic Features Vanessa ... text-level discourse parsing is crucial. Unlike syntactic parsing, where we are almost never interested in parsing above sentence level, sentence-level parsing is not suf...

Ngày tải lên: 07/03/2014, 18:20

... 348–352, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Hierarchical A ∗ Parsing with Bridge Outside Scores Adam Pauls and Dan Klein Computer Science Division University ... . , φ n with weights w 1 , . . . , w n , the conclu- sion φ 0 can be formed with weight g(w 1 , . . . , w n ) and priority p(w 1 , . . . , w n ). These deduction rules are “exe...

Ngày tải lên: 30/03/2014, 21:20

... Association for Computational Linguistics Transition-based parsing with Confidence-Weighted Classification Martin Haulrich Dept. of International Language Studies and Computational Linguistics Copenhagen ... confidence-weighted classifiers with transition-based dependency pars- ing yields results comparable with the state-of-the- art results achieved with Support Vector Machines - with...

Ngày tải lên: 20/02/2014, 04:20

... parsing Coarse-to-fine parsing (Charniak et al., 2006) is a technique to speed up parsing by exploiting the information that can be gained from parsing with simpler, coarser grammars—e.g., a grammar with a smaller ... our transformations. Figure 8 compares the parsing times of LCFRS with and without the new CFG-CTF method. The graph shows a steep incline for parsing with LC...

Ngày tải lên: 08/03/2014, 21:20

... Perl. 23 ate He He:1:2-ate:2:0 ate meat ate:1:0-meat:2:1 ate with ate:1:0 -with: 2:1 meat the the:1:2-meat:2:0 with fork with: 1:0-fork:2:1 fork a a:1:2-fork:2:0 Figure 4: Examples of bigram-subtrees ate meat with ate:1:0-meat:2:1 -with: 3:1 ate with ... of Eisner (1996). To use richer second-order information, we also imple- ment parent-child-grandchild features (Carreras, 2007) in...

Ngày tải lên: 16/03/2014, 23:20

... for Computational Linguistics:shortpapers, pages 699–703, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Improving Dependency Parsing with Semantic Classes ... results from parsing Pennconverter’s output are lower than with other conversions, Johansson and Nugues (2007) claim that this conversion is better suited for semantic processing, wit...

Ngày tải lên: 17/03/2014, 00:20

... Algorithms for Parsing the DOP Model. In Proceedings of EMNLP. Joshua Goodman. 1996b. Parsing Algorithms and Metrics. In Proceedings of ACL. Joshua Goodman. 2003. Efficient parsing of DOP with PCFG-reductions. ... compaction with negligible overhead in computation. 5 Improved Treebank Representations 5.1 Character-Level Parsing The all-fragments approach to parsing has the added...

Ngày tải lên: 23/03/2014, 16:20

... for Computational Linguistics:shortpapers, pages 212–216, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Language-Independent Parsing with Empty Elements Shu ... of CKY parsing allowing it to parse a word- lattice instead of a predetermined list of terminals. Lattice parsing adds a layer of flexibility to exist- ing parsing technology, and allow...

Ngày tải lên: 23/03/2014, 16:20

... efficient parsing with proof-nets Alain Lecomte GRIL Universit6 Blaise Pascal 63037-Clermont-Ferrand France email: lecomte@ shm.grenet.fr Abstract This paper presents a method for parsing ... method of chart -parsing. Ktnig [1991, 1992] was the first to apply chart -parsing to Lambek calculus. Hepple [1992] has recently improved this application. An obvious difference wi...

Ngày tải lên: 24/03/2014, 05:21

... pages 499–506, Ann Arbor, June 2005. c 2005 Association for Computational Linguistics Resume Information Extraction with Cascaded Hybrid Model Kun Yu Gang Guan Ming Zhou Department of Computer ... attached with labels indicating the information types. Then in the second pass, the detailed information, such as Name and Address, are identified in certain blocks (e.g. blocks labelle...

Ngày tải lên: 20/02/2014, 15:20