Báo cáo khoa học: "Using Search Engines for Robust Cross-Domain Named Entity Recognition" ppt

... Association for Computational Linguistics, pages 965–975, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Piggyback: Using Search Engines for Robust Cross-Domain Named ... words and phrases from search results for query expansion (Rocchio, 1971; Xu and Croft, 1996). Search counts or search results have also been used for sentimen...

Ngày tải lên: 23/03/2014, 16:20

... substantial research to support or challenge this view. In this paper, we investigate the following research ques- tion: Are parser output features helpful in mod- eling preposition usage in well-formed ... task of preposition selection on well-formed texts written by native speakers. For every preposition in the test set, we compare the system’s top preposition for that context to the wr...

Ngày tải lên: 30/03/2014, 21:20

... Volume), pages 93–96, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Using Structural Information for Identifying Similar Chinese Characters Chao-Lin Liu Jen-Hsiang ... pronunciations or in their internal structures are useful for computer-assisted language learning and for psycholinguistic studies. Al- though it is possible for us to emplo...

Ngày tải lên: 20/02/2014, 09:20

... 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 need for an automatic ... i.e. cognates that were not mistaken for others within a text window. Some were filtered out if they either lied outside an empirically defined search space, named a corridor, or were...

Ngày tải lên: 20/02/2014, 18:20

... into commercial search engines and compare different strategies for learning from search logs. The search logs consist of user queries and relevant search results retrieved by a search engine. We ... corpus of search queries with part- of-speech tags, providing a resource for future work on syntactic query analysis. 1 Introduction Syntactic analysis of search queries is im...

Ngày tải lên: 16/03/2014, 20:20

... To over- come these problems, we recast the search as one of searching for inconsistently-used elementary trees in a Tree Adjoining Grammar-based form of the tree- bank. This allows consistency ... and points on either side). See Dickinson and Meur- ers (2003b) for details. This work forms the basis for the DECCA system. 1 2.2 Motivation for Our Approach (2) a. NP qmp summit NP $rm...

Ngày tải lên: 17/03/2014, 00:20

... The results support the use of leading text as general purpose summaries for news documents. 2 Searchable LEAD Overview Searchable LEAD was originally implemented to provide LEXIS-NEXIS customers ... Longer documents, however, more often begin with anecdotal information before pre- senting the logical lead. LEAD fields must be longer for these documents in order to include the lo...

Ngày tải lên: 17/03/2014, 07:20

... more on the Chinese-side information than on the English-side information. Therefore, the Chinese-side informa- tion is more beneficial than the English-side in- formation. In order to show ... existing methods rely only on one-side information for sentence ranking, which is not very reliable. In order to leveraging both-side information for sentence ranking, we propose the followi...

Ngày tải lên: 30/03/2014, 21:20

... lan- guages, the English word forms often do not contain enough information for producing the correct fullform in the target language. We investigate meth- ods for improving the quality of such translations ... lexicon models including baseform and POS information for translation from German into English. Information contained in the German en- tries that are not relevant for the gene...

Ngày tải lên: 31/03/2014, 20:20

... framework for spec- ifying compositional nonparametric Bayesian models. Advances in Neural Information Processing Systems, 19:641. Philipp Koehn et al. 2007. Moses: Open source toolkit for statistical ... Distributed algorithms for topic models. Journal of Machine Learning Research, 10:1801–1828. Franz Josef Och, Christoph Tillmann, and Hermann Ney. 1999. Improved alignment models for...

Ngày tải lên: 20/02/2014, 04:20