Tài liệu Báo cáo khoa học: "An Improved Parser for Data-Oriented Lexical-Functional Analysis" doc

... An Improved Parser for Data-Oriented Lexical-Functional Analysis Rens Bod Informatics Research Institute, University of Leeds, Leeds LS2 9JT, UK, & Institute for Logic, Language ... frag- ment size is confirmed for LFG-DOP; (3) LFG- DOP's relative frequency estimator performs worse than a discounted frequency estimator; and (4) LFG-DOP significantly outperforms Tree- DO...

Ngày tải lên: 20/02/2014, 18:20

... competence and performance phenomena. The remaining constraints imposed at the level of the parser are traditionally treated as performance constraints. For example, the parser& apos;s bounded ... also a simple abstraction operation for SUG descriptions which allows unneeded informa- tion to be forgotten, as will be discussed in the section on the parser design. In an SUG deriv...

Ngày tải lên: 20/02/2014, 21:20

... 1 for the entire graph G. After this deletion, the splits for G with root fragments 2 and 3 are still eliminable; so we can e.g. delete the split for 3. At this point, only one split is left for ... by checking each split for eliminability before it is added to the chart. We compare the performance of this algorithm to the baseline of computing the complete chart. For comparison,...

Ngày tải lên: 20/02/2014, 12:20

... also be seen that combining phrase tables from multiple samples improved the BLEU score for HLEN, but not for HIER. This suggests that for HIER, most of the useful phrase pairs discovered by the ... Distributed algorithms for topic models. Journal of Machine Learning Research, 10:1801–1828. Franz Josef Och, Christoph Tillmann, and Hermann Ney. 1999. Improved alignment models for...

Ngày tải lên: 20/02/2014, 04:20

... statistical parsers (see (Yates et al., 2006)). While the average per- formance of statistical parsers gradually improves, the quality of many of the parses they produce is too low for applications. ... of parses whose f-score is at least that f-score. For the in-domain scenario, the parsers are tested on sec 23 of the WSJ Penn Treebank. For the parser adaptation scenario, they are te...

Ngày tải lên: 20/02/2014, 12:20

... Association for Computational Linguistics An Approximate Approach for Training Polynomial Kernel SVMs in Linear Time Yu-Chieh Wu Jie-Chi Yang Yue-Shi Lee Dept. of Computer Science and Information ... methods, for example support vector machines (SVM) (Vapnik, 1995) are successfully applied to many natural language processing (NLP) problems. They yielded very competitive and s...

Ngày tải lên: 20/02/2014, 12:20

... report belongs to the document). DocSim(M r , M) = |Doc( M r ) ∩ Doc( M )| |Doc( M r )| where M r is the reference report, M a second re- port and Doc( M r ), Doc( M) are the documents to which the ... set of selected documents (with different val- ues for n and different sets of documents) and b) taking the full content of a few doc- uments. In both cases, document sets are formed w...

Ngày tải lên: 20/02/2014, 15:20

... quantity, predictive information gain, predictive information redundancy and predictive information summation. Predictive Information Quantity (PIQ) );( RFPIQ , the predictive information quantity of ... reliable reference for feature type selection in the probabilistic evaluation modelling for statistical syntactic parsing. 3 The information-theory-based feature type analysis model fo...

Ngày tải lên: 20/02/2014, 18:20

... methodological concerns. Finally, when other platforms usually enforce the use of a dedicated document format, LinguaStream is able to process any XML document. On the other hand, LinguaStream is ... that the LinguaStream platform promotes the combination of purely declarative formalisms (when GATE is mostly based on the JAPE language and NOOJ focuses on a unique formalism), and allows proces...

Ngày tải lên: 22/02/2014, 02:20

... tree description and/or of semantic formu- las. The XMG formalism furthermore supports the sharing of identifiers across dimension hence al- lowing for a straightforward encoding of the syn- tax/semantics ... frame- work for the processing of linguistic meta- descriptions. 1 Introduction It is well known that grammar engineering is a complex task and that factorizing grammar in- formation...

Ngày tải lên: 22/02/2014, 02:20