Tài liệu Báo cáo khoa học: "Head-Driven Parsing for Word Lattices" ppt

... information are both critical for high performance. To avoid a trade- off between these two, we need to increase parsing speed, but without losing accuracy. Parsing with lexicalised grammar formalisms, such ... enough for wide coverage parsing using multi-tagging (Chen et al., 1999), in which more than one supertag can be assigned to a word; however, as more su- pertags are supplie...

Ngày tải lên: 20/02/2014, 04:20

... head words. We present O(n 4) parsing algorithms for two bilexical formalisms, improv- ing the prior upper bounds of O(n5). For a com- mon special case that was known to allow O(n 3) parsing ... pand the start word $ E VT into xSy for some (x, y) E L(H$), and then recursively expand the words in strings x and y. More formally, given H, we simultaneously define La for all...

Ngày tải lên: 20/02/2014, 19:20

... them. 2.1 Constructing Translation Forests The parsing stage builds a forest of derivations by parsing with the source-side projection of the syn- chronous grammar. Each forest node P ij com- pactly ... Transforming the entire for- est to n-ary form is intractable, however, because the number of hyperedges would be exponential in n. Instead, we include only the top k n-ary back- traces...

Ngày tải lên: 20/02/2014, 09:20

... systems in widespread use for storing symbolic information. The AI community, of course, has a number of methods for maintaining more sophisticated knowledge bases of, say, formulas in first-order ... viability for some time. Fortunately, the linguistic coverage of several current systems appears to be adequate for many practical purposes, so commercialization need not wait fo...

Ngày tải lên: 21/02/2014, 20:20

... new state-of-the-art semantic parsing model, propose a broader theory for tree transforma- tion based semantic parsing, and present a general inference algorithm for the tree transducer frame- work. ... priors. For our manually set priors, we explore different hyper-parameter set- tings for three different priors, one for each of the main decision types: MR rule, NL pattern, and...

Ngày tải lên: 19/02/2014, 19:20

... error. To do this, we added the gold category for a word to the set of possible tags con- sidered for that word by the supertagger. This was done for categories that the supertagger could use; categories ... supertagging, on parsing accuracy. 1 Introduction Reranking techniques are commonly used for im- proving the accuracy of parsing (Charniak and John- son, 2005). Efficient d...

Ngày tải lên: 19/02/2014, 19:20

... June 2008. c 2008 Association for Computational Linguistics Self-Training for Biomedical Parsing David McClosky and Eugene Charniak Brown Laboratory for Linguistic Information Processing (BLLIP) Brown ... al., 2006a; McClosky et al., 2006b). One possible use for this technique is for parser adaptation — initially training the parser on one type of data for which hand-labeled tr...

Ngày tải lên: 20/02/2014, 09:20

Ngày tải lên: 20/02/2014, 18:20

... of a 2000 word lexicon and a morphological analyzer. The lexicon contains, for each word, a list of possible lexical categories, subcategorization information, and in a few cases, information ... compound words. For example, the entry for round states that it is a noun, verb, adjective or preposition, that as a verb it is subcategorized for the movable particles out and u...

Ngày tải lên: 21/02/2014, 20:20

... partner. In contrast to other work on discourse parsing, we wish to use the parsing process directly for di- alog management (rather than for information ex- traction or summarization). This inuences ... to improved performance for any method. One utterance of context is best for shift-reduce and start-join; three is best for the connection path method. The shift- reduce method...

Ngày tải lên: 22/02/2014, 02:20