Báo cáo khoa học: "An Integrated Term-Based Corpus Query System" pptx

... corresponding GUI-driven query formulation offer a flexible way of querying a terminologically processed corpus. The corpus mining process is performed in the following steps: A literature corpus is POS ... relationships between terms and their contexts. Query are defined via GUI, and are translated into the XQuery language. XQuery, 2 an XML query language, is used as an underlyi...

Ngày tải lên: 08/03/2014, 21:20

... AN INTEGRATED HEURISTIC SCHEME FOR PARTIAL PARSE EVALUATION Alon Lavie School of Computer Science ... parsable subsets of the original input. This paper describes recent work on de- veloping an integrated heuristic scheme for selecting the parse that is deemed "best" from such a

Ngày tải lên: 20/02/2014, 21:20

... LinguaStream: An Integrated Environment for Computational Linguistics Experimentation Fr ´ ed ´ erik Bilhaut GREYC-CNRS University ... models can be evalu- ated either with regard to their ability to account for the reality of a given corpus (pursuing descrip- tive aims), either with regard to their ability to analyse it accurately ... relies on the pipeline paradigm). Also, the 1 Formerl...

Ngày tải lên: 22/02/2014, 02:20

... efficiency. In (Becker and Frank, 2002) we present a corpus- driven stochastic topological parser for German, based on a topological restructuring of the NEGRA corpus (Brants et al., 1999). For topological ... coverage of the deep system on the whole corpus, which resulted in 28.6% of the sentences being fully lexically analyzed. The corresponding experiment with the integrated system y...

Ngày tải lên: 08/03/2014, 07:20

... referring expression module at the final stage of the genera- tion process. 3 Corpus Study The generator is informed by a corpus study of em- bedded discourse units on two discourse annotated corpora: ... 640 Table 1: Syntactic types of parentheticals in the RST corpus Relation Connective in parenthetical Connective in host distribution in corpus TEMPORAL 101 (48.8%) 2 3434 (18.6%) CON...

Ngày tải lên: 23/03/2014, 17:20

... fr/Individu/j acquemi/FASTK. from 15 Proceedings of EACL '99 Raw corpus P-O-Ssy/exTagging ~ ] I L,emmatizcd and tagged corpus Term Extraction LEXTER I Network of term candidates Term ... acquires and uses corpus- based selection restrictions of adjectives and nouns (Bourigault et al., 1996). For example, in order to disambiguate PP- attachments, the system possesses...

Ngày tải lên: 24/03/2014, 03:20

... related to the given query. The other is general words that are not significant for the specified document set. The two types of words are filtered through two features, i.e. query- relevance ... query- relevance and topic-specificity. The query- relevance of a word is defined as the proportion of the number of sentences that contains both the word and at least one query word...

Ngày tải lên: 31/03/2014, 00:20

... inspection, editing, or reuse. IRACQ is also integrated with the other acquisition facilities available. As the example session above illustrates, IRACQ is integrated with KREME, a knowledge representation ... IRACQ session. 4.3 Debugging environment The facility for creating and extending IRules is integrated with the IRUS NLI itself, so that debugging can commence as soon as...

Ngày tải lên: 08/03/2014, 18:20

... techniques for translation and speech recognition. Xerox Research Centre Europe, Grenoble (France): corpus provider and statistical translation modeling. Celer Soluciones, Madrid (Spain): evaluation

Ngày tải lên: 17/03/2014, 06:20

... al. 2004). TEG is a hybrid rule-based and statistical IE system. It utilizes a trained labeled corpus in order to com- plement and enhance the performance of a rela- tively small set of manually-built ... adapted to any domain by writing a suitable set of rules, and training them using an annotated corpus. The TEG rule lan- guage is a straightforward extension of a con- text-free gramm...

Ngày tải lên: 23/03/2014, 18:20