parsing with discontinuous constituents

Ngày tải lên: 31/03/2014, 17:20

... so-called discontinuous constituents. We have discontinuous noun phrases in (5) and (7), a discontinuous adjective phrase in (3), discontinuous verb phrases in (1) and (4), and a discontinuous ... GPSG, with the effect that such grammars generate trees with discontinuities for sentences with discontinuous constituents, while everything else remains the same. 4. Phrase-structure rules with ... adjacency in discontinuous tre es. 3. Adjacency in phrase-structure rules for discontinuous constituents A phrase-structure rule rewrites a constituent into a sequence of pairwise adjacent constituents. ...

Ngày tải lên: 09/03/2014, 01:20

... a pattern with which to expand it and then filling out that pattern with words drawn from a unigram distribution. This kind of coupled generative process can be naturally formalized with tree ... accuracy (the percentage of sentences with correct answers), as well as F1: the harmonic mean of precision (the proportion of correct answers out of sentences with a parse) and recall (the proportion ... facilitates a greater flow of ideas in the research community, allowing semantic parsing to leverage ideas from other work with tree automata, while making clearer how seemingly isolated ef- forts might...

Ngày tải lên: 19/02/2014, 19:20

... statistical parsing with CCG and Log-Linear models. Computational Linguistics, 33(4):493–552. S. Clark, J. Hockenmaier, and M. Steedman. 2002. Building deep dependency structures with a wide- coverage ... required to both train and parse with the Petrov parser on the Penn Treebank, the Petrov parser on the original version of CCGbank, the Petrov parser on CCGbank without features and the Clark and ... features and the Clark and Curran parser using the two mod- els. All training and parsing was done on a 64-bit machine with 8 dual core 2.8 Ghz Opteron 8220 CPUs and 64GB of RAM. Our training times...

Ngày tải lên: 20/02/2014, 04:20

... 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 faster training and parsing times. ... ex- periments with using CW-classifiers in transition- based parsing. 5.1 Online classifiers We compare CW-classifiers with other online al- gorithms for linear classification. We compare with perceptron ... feature selection has been used for languages marked with an *. curacy a lot. In this section we will compare re- sults obtained with CW-classifiers with the results for the MaltParser from CoNNL-X....

Ngày tải lên: 20/02/2014, 04:20

... for Statistical Parsing with Combinatory Categorial Grammar. In Proceedings of the 40th Annual Meeting of the ACL. Julia Hockenmaier. 2003. Data and Models for Statistical Parsing with CCG. Ph.D. ... First, head constituents have to be fully expanded before non-head constituents are generated. Second, words have to be generated at the leaves of the tree, not at the maximal projection of constituents. 5.3 ... derivation tree itself. It as- sumes that binary trees (with parent category ) have one head child (with category ) and one non- head child (with category ), and that each node has one lexical head ....

Ngày tải lên: 20/02/2014, 16:20

Ngày tải lên: 20/02/2014, 18:20

... all reductions at a given point with rules with the same number of daughters, the packed sequences can be formed into higher-level constituents as they stand without further processing. However, ... unification-based gram- mars: in particular, with grammars admitting less ambiguity parse time will tend to increase more slowly with increasing input length, and also with smaller grammars rule application ... on Artificial Intelligence. 703-708. 293 RELATING COMPLEXITY TO PRACTICAL PERFORMANCE IN PARSING WITH WIDE-COVERAGE UNIFICATION GRAMMARS John Carroll University of Cambridge, Computer Laboratory...

Ngày tải lên: 20/02/2014, 21:20

... 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 sufficient for discourse parsing. While ... discourse parsing is consistently infe- rior to that within individual sentences, and we will briefly discuss what the key difficulties with extend- ing sentence-level to text-level discourse parsing ... text. Text-level discourse parsing imposes more con- straints on the global coherence than sentence-level discourse parsing. However, if, technically speak- ing, text-level discourse parsing were no more...

Ngày tải lên: 07/03/2014, 18:20

... focus on the use of LCFRS for parsing with discontinuous constituents. This follows up on recent work on parsing the discontinuous anno- tations in German corpora with LCFRS (Maier, 2010; van ... Negra with the same setup as in section 3.3. We report discontinuous F 1 scores as well as exact match scores. For previous results on discontinuous parsing with Negra, see table 3. For results with ... work on parsing the Wall Street journal corpus in which traces have been converted to discontinuous con- stituents (Evang and Kallmeyer, 2011). In the case of parsing with discontinuous constituents...

Ngày tải lên: 08/03/2014, 21:20

... of the EDOL hypothesis with respect to those dependencies that are being checked by the parser. 2 Parsing Unification-Based Grammars In phrase-structure rule-based parsing, each rule corresponds ... since the same rule may be used several times within a single derivation, and also the same constituent may be used within different partial analyses with features instantiated in dif- ferent ... effect on parsing effi- ciency. However, the problem of grammar size in TAG has to some extent been addressed both with respect to grammar encoding (Evans et al., 1995; Candito, 1996) and parsing...

Ngày tải lên: 08/03/2014, 21:20

... larity, and with either the same path or with path p. Also, in leaves of a proof in L (/'\'v), categories only occur with zero path. Therefore, if we have 124 Parsing with polymorphism ... sequent with a positive occurrence of ViX.X/X and with non-zero path, then there must occur higher in the proof, a sequent with V,.X.X/X occurring again positively and this time with with zero-path. ... So parsing with an L(/,\) grammar comes to decid- ing the derivability of Xl, , xo =:~ s, where xi are the categories of the lexical items. This Lambek style of grammar is associated also with...

Ngày tải lên: 09/03/2014, 01:20

... lower nodes from higher nodes with a statistical model. To improve parsing flexibility in deterministic parsing, our top-down parser uses beam search al- gorithm with dynamic programming (Huang ... the proposed algo- rithm achieves comparable results with other data-driven dependency parsing algorithms. 1 Introduction Transition-based parsing algorithms, such as shift- reduce algorithms ... 166–170. M. Collins and B. Roark. 2004. Incremental parsing with the perceptron algorithm. In Proc. the 42nd ACL. J. Earley. 1970. An efficient context-free parsing algo- rithm. Communications of the Association...

Ngày tải lên: 16/03/2014, 19:20

... Models without QG with QG O2 79.67 81.04 (+1.37) O2sib 79.25 80.45 (+1.20) O1 76.73 79.04 (+2.31) Li11 joint 80.79 — Li11 pipeline 79.29 — Table 5: Parsing accuracy (UAS) comparison on CTB5- test with ... boost the state-of- the-art parsing accuracy by a large margin. Li et al. (2011) show that a joint POS tagging and de- pendency parsing model can significantly improve parsing accuracy over a pipeline ... with 21 sibling TPs and 22 grand TPs. Based on these TPs, we propose the QG fea- tures for enhancing the baseline parsing models, which are shown in Table 2. The type of the TP is conjoined with...

Ngày tải lên: 16/03/2014, 19:20

... Linguistics. 29 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 ... ate:1:0-NULL:2:1-meat:3:1 the:1:3-NULL:2:3-meat:3:0 a:1:3-NULL:2:3-fork:3:0 with: 1:0-NULL:2:1-fork:3:1 ate:1:0-the:2:3-meat:3:1 ate:1:0 -with: 2:1-fork:3:2 with: 1:0-a:2:3-fork:3:1 NULL:1:2-He:2:3-ate:3:0 He:1:3-NULL:2:1-ate:3:0 ate:1:0-meat:2:1-NULL:3:2 ate:1:0-NULL:2:3 -with: 3:1 with: 1:0-fork:2:1-NULL:3:2 NULL:1:2-a:2:3-fork:3:0 a:1:3-NULL:2:1-fork:3:0 ate:1:0-NULL:2:3 ... projec- tive parsing algorithm of Eisner (1996). To use richer second-order information, we also imple- ment parent-child-grandchild features (Carreras, 2007) in the MST parsing algorithm. 3.1 Parsing with...

Ngày tải lên: 16/03/2014, 23:20

... Improving parsing and PP attachment perform- ance with sense information. In Proceedings of ACL- 08: HLT, pages 317–325, Columbus, Ohio. Daniel M. Bikel. 2004. Intricacies of Collins’ parsing ... G. Attardi. 2007. Dependency Parsing with Second-Order Feature Maps and Annotated Se- mantic Information, In Proceedings of the 10th In- ternational Conference on Parsing Technology. Eugene ... 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, with a richer...

Ngày tải lên: 17/03/2014, 00:20

Ngày tải lên: 17/03/2014, 02:20

Ngày tải lên: 17/03/2014, 02:20

Ngày tải lên: 17/03/2014, 04:20

Ngày tải lên: 17/03/2014, 04:20