Tài liệu Báo cáo khoa học: "Exploiting Non-local Features for Spoken Language Understanding" pptx

... Psychology Stanford University Stanford, California mcfrank@Stanford.edu Abstract This paper uses an unsupervised model of grounded language acquisition to study the role that social cues play in language ... strong support for the view that social cues are a crucial information source for grounded language learning. We also showed that the importance of the differ- ent social cues...

Ngày tải lên: 19/02/2014, 19:20

... addressed. First, we show how features can be generated for arbitrary head-argument configurations. Affinity features are relatively straightforward, but paraphrase features, which have been hand-developed ... reduction over the non-local syntactic features used in Huang (2008). Our web- scale features reduce errors for a range of attachment types. Finally, we present an analysi...

Ngày tải lên: 20/02/2014, 04:20

... con- sistently outperforms the similarity-based baseline on all the lecture datasets. We attribute this gain to the presence of more attenuated topic transi- tions in spoken language. Since spoken language is ... representing nodes, the threshold distances for discarding node edges, the number of uniform chunks for estimating tf-idf lexical weights, the alpha parameter for smooth...

Ngày tải lên: 20/02/2014, 11:21

... the found set of features for text classification (index- ing) for an OIR query of the first level (finds opin- ionated information) and for an OIR query of the second level (finds opinionated information ... politics. We therefore believe that a system capable of pro- viding access to opinionated information in other languages (especially in Chinese) might be of great use for individua...

Ngày tải lên: 20/02/2014, 12:20

... Caparica Portugal Abstract This paper describes a language independent method for alignment of parallel texts that makes use of homograph tokens for each pair of languages. In order to filter out tokens ... longer afford to waste human time and effort building manually these ever changing and in- complete databases or design language specific applications to solve this problem. The ne...

Ngày tải lên: 20/02/2014, 18:20

... derivations for spoken utterances that would be allowed for the equivalent written sentences. For ex- ample, consider the derivations that it permits for ex- ample (16) above. The rule of forward ... yield canon- ical function-argument structure, or "logical form". There may be significant advantages for automatic spoken language understanding in such a theory....

Ngày tải lên: 08/03/2014, 18:20

... 202–210, Athens, Greece, 30 March – 3 April 2009. c 2009 Association for Computational Linguistics Re-Ranking Models For Spoken Language Understanding Marco Dinarelli University of Trento Italy dinarelli@disi.unitn.it Alessandro ... Riccardi University of Trento Italy riccardi@disi.unitn.it Abstract Spoken Language Understanding aims at mapping a natural language spoken sen-...

Ngày tải lên: 08/03/2014, 21:20

... halting a perceived decline in the English language. He argues that language and thought form a tight feedback cycle that can be either virtuous or vi- cious. Lazy language can thus promote lazy think- ing, ... a modest form of linguistic creativity. 1 Introduction In a much-quoted essay from 1946 entitled Politics and the English Language, the writer and thinker George Orwell outlines...

Ngày tải lên: 20/02/2014, 05:20

... Association for Computational Linguistics Exploiting N-best Hypotheses for SMT Self-Enhancement Boxing Chen, Min Zhang, Aiti Aw and Haizhou Li Department of Human Language Technology Institute for ... posterior knowledge, namely, language model, translation model and word reordering. 157 2.1 Language Model We consider self-enhancement of language model as a language...

Ngày tải lên: 20/02/2014, 09:20

... ap- proach to exploit non-local information in the next section. 3 Incorporating Non-local Information 3.1 Using Trigger Features To exploit non-local information to sequential la- beling for a statistical ... selec- tion algorithm is very efficient for both perfor- mance and time complexity. 2 Spoken Language Understanding as a Sequential Labeling Problem 2.1 Spoken Languag...

Ngày tải lên: 20/02/2014, 12:20