exploiting heterogeneous treebanks for parsing

... problem of how to use these heterogeneous treebanks for target gram- mar parsing. Here heterogeneous treebanks refer to two or more treebanks with different grammar formalisms, e.g., one treebank ... heteroge- neous treebanks for parsing by breaking it down into two sub-problems, convert- ing grammar formalisms of the treebanks to the same one, and parsing on these homogeneous treebanks. First ... Parsing Through grammar formalism conversion, we have successfully turned the problem of using hetero- geneous treebanks for parsing into the problem of parsing on homogeneous treebanks. Before using converted...

Ngày tải lên: 17/03/2014, 01:20

... Association for Computational Linguistics Exploiting Multiple Treebanks for Parsing with Quasi-synchronous Grammars Zhenghua Li, Ting Liu ∗ , Wanxiang Che Research Center for Social Computing and Information ... philosophy, these treebanks contain rich human knowledge on the Chinese syntax, thereby having a great deal of common ground. Therefore, exploiting multiple treebanks is very attractive for boosting parsing ... present a simple and effective framework for exploiting multiple monolingual treebanks with different annotation guidelines for pars- ing. Several types of transformation patterns (TP) are designed...

Ngày tải lên: 16/03/2014, 19:20

... any information about repair is stripped from the input, including partial words, repair sym- bols 3 , and interruption point information. While an integrated system for processing and parsing ... results from Hale et al. RCT results are on the right-corner transformed grammar (transformed back to flat treebank-style trees for scoring purposes). CYK and TAG lines show relevant results from ... syntactic information to find repairs, and thus may have access to some of this information about where interruptions occur, this experiment is intended to evaluate the use of the right corner transform...

Ngày tải lên: 20/02/2014, 09:20

... “straightforward”, “likeable” (class 2). Some unexpected distinguish- ing terms for this author are “lion” for class 2 (three- class case), and for class 2 in the four-class case, “jennifer”, for ... deviation of PSP for reviews expressing different ratings. But before proceeding, we note that it is possi- ble that similarity information might yield no extra benefit at all. For instance, we ... Jonathan Schler. 2005. The importance of neutral examples for learning sentiment. In Workshop on the Analysis of Informal and Formal Information Exchange during Negotiations (FINEXIN). Liu, Hugo,...

Ngày tải lên: 20/02/2014, 15:20

... Statistical Pattern Recognition. Doctoral dissertation. Stanford University, Stanford, Cali- fornia. 283 Statistical Decision-Tree Models for Parsing* David M. Magerman Bolt Beranek and Newman ... sentence length for Wall Street Journal experiments. 5 Conclusion Regardless of what techniques are used for parsing disambiguation, one thing is clear: if a particular piece of information is ... and 7 illustrate the performance of SPATTER as a function of sentence length. SPAT- TER's performance degrades slowly for sentences up to around 28 words, and performs more poorly and more...

Ngày tải lên: 20/02/2014, 22:20

... surrounding channel then forms a training example for a supervised WSD program in the next step. The average time taken to perform manual se- lection of target translations for one SENSEVAL-2 English ... nouns. For instance, no oc- currences of sense 5 of the noun circuit (racing circuit, a racetrack for automobile races) could be found in the parallel corpora. To ensure a fairer comparison, for ... train- ing examples found for each sense of w in the cor- responding parallel text training set that gave rise to the accuracy figure P2 for w. The accuracy fig- ures thus obtained for the difficult...

Ngày tải lên: 08/03/2014, 04:22

... quantitatively estimated by exploiting the redundancy of Web information. Experiments carried out on the TREC-2001 judged-answer collec- tion show that the approach achieves a high level of performance (i.e. ... Association for between the success rates obtained for the named entity questions (Table 3) and the full TREC-2001 question set (Table 2) is 5.1%. This means that our approach performs better ... its high performance as proof for the difference between our task and classic co- occurrence mining. Another indication for this is the fact that MLHR and PMI performances are compa- rable, however...

Ngày tải lên: 08/03/2014, 07:20

... (Fig- ure 1): one for the live “instant translation” user interface, one for demonstrating the different com- ponents of the system and algorithmic visualiza- tions, and one designated for technical ... and David Chiang. 2005. Better k-best parsing. In Proceedings of the International Work- shop on Parsing Technologies. 27 We will rely on 3 workstations: one for the instant translation demo, ... Open source toolkit for statistical machine translation. In Proceedings of the ACL-2007 Demo and Poster Ses- sions. Zhifei Li and Sanjeev Khudanpur. 2008. A scalable decoder for parsing- based machine...

Ngày tải lên: 17/03/2014, 02:20

Ngày tải lên: 17/03/2014, 06:20

Ngày tải lên: 23/03/2014, 17:20

Ngày tải lên: 23/03/2014, 20:20

Ngày tải lên: 24/03/2014, 05:21

Ngày tải lên: 30/03/2014, 16:20

Ngày tải lên: 30/03/2014, 21:20

Ngày tải lên: 31/03/2014, 06:20

Ngày tải lên: 31/03/2014, 18:20

Ngày tải lên: 21/06/2014, 22:20

Ngày tải lên: 23/06/2014, 01:20

... structure without a compilation step. For more information on JDOM, visit http://www.jdom.org. For information on the Java Community Process (JCP) standards effort for JDOM, see JSR 102. DOM4J Although ... Overview javax.xml.transform Defines the TransformerFactory and Transformer classes, which you use to get a object capable of doing transformations. After creating a transformer object, you invoke its transform() ... initiative by the United Nations (UN/CEFACT) and the Organization for the Advancement of Structured Information Systems (OASIS). For more information on ebXML, see http://www.ebxml.org/. cxml Commerce...

Ngày tải lên: 16/10/2013, 12:15

... 2–21 for training, 22 for development and 23 for testing). We also used section 2 as a small training set for evaluating the performance of our model under low-resource conditions. Hence- forth, ... with the TSG model for further fitting the training set and improving the parsing accuracy. The performance of the SR-TSG parser was strongly affected by its backoff models. For exam- ple, the ... (2005) 92.0 91.4 Huang (2008) 92.3 91.7 Table 3: Our parsing performance for the testing set compared with those of other parsers. *Results for the development set (≤ 100). structural ambiguities...

Ngày tải lên: 19/02/2014, 19:20