Tài liệu Báo cáo khoa học: "Fast Online Lexicon Learning for Grounded Language Acquisition" pdf

... Association for Computational Linguistics, pages 430–439, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Fast Online Lexicon Learning for Grounded Language ... of the Association for Computational Linguistics (ACL-10). Luke S. Zettlemoyer and Michael Collins. 2007. Online learning of relaxed CCG grammars for parsing to logi-...

Ngày tải lên: 19/02/2014, 19:20

... performed about the same as random selection for the NE task, while for the parsing task extrinsic selection per- formed markedly worse. This shows that examples that were very informative for ... were not that informative for the parse learner. 2.3 Protocols for Multi-Task AL Obviously, we can expect one-sided selection to per- form better for the reference learner (the one for...

Ngày tải lên: 20/02/2014, 09:20

... improve performance on the statistical spoken language understanding (SLU) problem. The statistical natural language parsers trained on text perform unreliably to encode non-local informa- tion ... in vari- ous natural language tasks. Thus, we need new methods to import non-local information into se- quential models. There are two types of method for using non- local information. One...

Ngày tải lên: 20/02/2014, 12:20

... language. Those lexicon models lack from context infor- mation that can be extracted from the same paral- lel corpus. This additional information could be: Simple context information: information of the ... formulated as fol- lows: A source language string is to be translated into a target language string . In the experiments reported in this paper, the source language is German and...

Ngày tải lên: 20/02/2014, 18:20

... exists for physician SPECIALTIES, we can nonetheless give a rule for this predicate in way that is uniform with the rule given for the predicate PATIENTS. 2This term, while a standard one in formal ... issues for natural -language systems which serve as interfaces to a database: the problems that arise in a module which maps the meaning representation to a second logical lang...

Ngày tải lên: 21/02/2014, 20:20

... article in PDF format 3 on the system. • The document is processed by the open- source Grobid tool (see section 3) to extract 3 The commonly used publishing format is PDF files while authoring format ... approach is to work on the PDF file and not on these source formats. The rationale being that 1/ the source format is almost never available, 2/ even if we had access to the source format...

Ngày tải lên: 22/02/2014, 03:20

... performance. The premise of this dynamic model selection is that the domain-specific model performs better for input sentences similar to its training space, whereas the generalized model performs ... classes are derived selectively for our case. Given a word-form, we count how often each POS tag is used with the form and keep only ones above a certain threshold. For both generalized and...

Ngày tải lên: 19/02/2014, 19:20

... 2011. c 2011 Association for Computational Linguistics A Mobile Touchable Application for Online Topic Graph Extraction and Exploration of Web Content G ¨ unter Neumann and Sven Schmeier Language Technology ... can explore in an uniform way both new information nuggets and validated back- ground information nuggets interactively. Fig. 1 summarizes the main components and the informa-...

Ngày tải lên: 20/02/2014, 05:20

... unsupervised learning algorithm for inducing this parser from plain text. The parser uses a representation for syntactic structure similar to dependency links which is well-suited for incremental ... restricts the search space for both learning and parsing. The represen- tation the parser uses is designed for incremental parsing and allows a prefix of an utterance to be parsed be...

Ngày tải lên: 20/02/2014, 12:20

... methods for online machine learning algorithms. The update methods are based on a multinomial logistic model. Their performance is on par with other state-of-the-art on- line learning algorithms for ... 1999). Algorithm 1 General form of online algorithms input Training set T = {(x t , y t )} T t=1 Number of iterations N for n in 1 N for (x t , y t ) in T Compute update vector...

Ngày tải lên: 20/02/2014, 12:20