Báo cáo khoa học: "Experiments in Parallel-Text Based Grammar Induction" pdf

... incorporating additional semantic constraints in the class-instance acqui- sition process, which for the experiments in this paper were derived from instance-attribute pairs available in an independently ... incorporation of other kinds of semantic constraint for improved class-instance acquisition, further investigation into per-node sparsity con- straints in graph -based SSL, and m...

Ngày tải lên: 07/03/2014, 22:20

... that exploiting all contiguous word blocks in phrase -based align- ment is better than focusing on syntactic constituents only. In our context, we are interested in inducing syntactic constituents based ... substantial existing work in grammar in- duction: we construe the learning problem as PCFG induction, using the inside-outside algorithm, with the addition of weighting fact...

Ngày tải lên: 23/03/2014, 19:20

... a deepening of the lines be- tween the eyebrows, indicating concentration, deter- mination, opposition or hostility.” Definitions of this kind are again not easily handled in machine opera- ... adequate for our purposes. In giving a synonym definition, we are making use of a more general idea, namely, that of defining the intra- linguistic meaning of a word in terms of its relation...

Ngày tải lên: 19/02/2014, 19:20

... original structure of the grammar (e.g. turning inequa- tions in finite domains into disjunctions, map- ping constraining equations onto defining ones, if the automatic inference of the proper ... important to investigate the migration of the source formalism as is. Note that the resulting ALEP specification in (2) is as compact, perspicuous and maintainable as in any rule b...

Ngày tải lên: 22/02/2014, 10:20

... compo- nent utilizing any theory, including Centering the- ory. We thus now turn our attention to what role this information plays in a pronominalization algorithm. 5 A Simple Pronominalization Algorithm At ... during parsing, they ig- nore structures such as the discourse plan which are present during generation but not parsing. A typi- cal discourse plan can include vital information for...

Ngày tải lên: 08/03/2014, 07:20

... implementations of AN, TRF, and GEN. In this paper, we are not interested in the implementations, but in the relations to be implemented. Especially, we try to find a principled basis for the study ... TRANSFER IN A MULTILINGUAL MT SYSTEM Steven Krauwer & Louis des Tombe Institute for General Linguistics Utrecht State University Trans 14, 3512 JK Utrecht, The Netherlands...

Ngày tải lên: 08/03/2014, 18:20

... These accompa- nying examples reflect information in the surrounding text, and in turn, also influence the text. Sometimes, examples replace possible (textual) elaborations in the description. ... of integrated example and language generation. In this paper, we build upon some of these stud- ies and describe the issues in generating descriptions which include examples in a...

Ngày tải lên: 31/03/2014, 06:20

... Broad  the  firm  specializing  a  flat vystayba odmitnout instit. investor jmenovat construction decline instit. investor name constniction decline instit. investor name construction decline name instit. investor construction decline to name instit. investor construction decline to name DEF instit. investor construction declined to name the instit. investors Figure ... of both training...

Ngày tải lên: 31/03/2014, 20:20

... texts as input and transforms each into an equivalent data structure that contains both the original information (thus permitting a reconstruc- tion of the original text) and some new information ... position in the first record, and pointers to pos- sibly following occurrences of the word and to the beginning of the paragraph (concordance) that contains the word. Once the finished...

Ngày tải lên: 01/04/2014, 00:20

... classification margin in the training data (taking or not taking into account the derivational ambiguity). This option leverages a large amount of manual domain knowledge en- gineering and is not in general ... providing a clean testbed for investigating the effects of grammar extraction. We achieve substantial improvements against a number of baselines including EM, support vector machi...

Ngày tải lên: 07/03/2014, 22:20