Báo cáo khoa học: "Linguistically Motivated Large-Scale NLP with C&C and Boxer" ppt
... the ACL 2007 Demo and Poster Sessions, pages 33–36, Prague, June 2007. c 2007 Association for Computational Linguistics Linguistically Motivated Large-Scale NLP with C&C and Boxer James R. ... language, together with advances in wide-coverage grammar development, have led to high levels of robustness and efficiency in NLP systems and made linguistically motivated la...
Ngày tải lên: 31/03/2014, 01:20
... training and evaluation purposes, we used a random split of the collection into 90% training and 10% test. This yields a training corpus of 259 docu- ments and a test data set of 30 documents. 2.2 Candidate ... contributors, and follow the gen- eral guidelines of annotation provided by Wikipedia. The guidelines coincide with the goals of keyword extraction, and thus the Wikipedia...
Ngày tải lên: 08/03/2014, 01:20
... achieved with about 1OO general-purpose primitives like THING and WHERE for a vocabulary containing words like "transistor", "oscillator" and "circuit"; and with ... contents into knowledge bases. Indexing has its own proper function and hence utility, and can be successfully done without deep understanding of the texts being processed. Insof...
Ngày tải lên: 17/03/2014, 19:21
Tài liệu Báo cáo khoa học: Roles of heat shock factors in gametogenesis and development pptx
... occurrence between E7.5 and birth [63]. This would be compatible with aneuploidy and consis- tent with meiotic defects. HSF1 controls spindle for- mation and migration during oogenesis, and HSF2 has been ... are low and HSF2 display cytoplasmic and dendritic local- ization [125]. HSF2 expression and activity profiles are consistent with a major role for HSF2 as a transcrip-...
Ngày tải lên: 18/02/2014, 04:20
Tài liệu Báo cáo khoa học: "An Unsupervised Model for Joint Phrase Alignment and Extraction" ppt
... tuning and testing on specified development and test sets. We compare the accuracy of our proposed method of joint phrase alignment and extraction using the FLAT, HIER and HLEN models, with a ... models, and for the LM we use an interpolated Kneser-Ney 5-gram model. For GIZA ++, we use the standard training reg- imen up to Model 4, and combine alignments with grow-diag-final -a...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "Generative Power of CCGs with Generalized Type-Raised Categories" pptx
... Combinatory Categorial Grammars (CCGs) augmented with a linguistically -motivated form of type raising involving variables is weakly equivalent to the standard CCGs not involving variables. The proof ... Grammars and Tree Adjoining Grammars (Joshi, Vijay- Shanker, and Weir, 1991; Vijay-Shanker and Weir, 1994). But CCG-Std cannot handle the generalization of type raising that...
Ngày tải lên: 22/02/2014, 03:20
Báo cáo khoa học: "Computing Term Translation Probabilities with Generalized Latent Semantic Analysis" pptx
... representing dimensions of the document vectors with distri- butional term clusters (Bekkerman et al., 2003) and expanding the document and query vectors with synonyms and related terms as discussed in (Levow ... = w∈d i v∈d j α d i w β d j v w, v, (3) where α d i w and β d j v represent the weight of the terms w and v with respect to the documents d i and d j , res...
Ngày tải lên: 08/03/2014, 21:20
Báo cáo khoa học: "Subjective Natural Language Problems: Motivations, Applications, Characterizations, and Implications" pptx
... affective NLP or affective interfac- ing (Liu et al, 2003; Holzman and Pottenger, 2003; Francisco and Gerv ´ as, 2006; Kalra and Karahalios, 2005; G ´ en ´ ereux and Evans, 2006; Mihalcea and Liu, 2006). ... non-traditional intersubjectivity, variation in human behavior, and recognition of absence of real ‘ground truth’ may be quite useful to understand and appropriately model...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "A SNoW based Supertagger with Application to NP Chunking" ppt
... 02-14 and 21-24, and it is tuned with 44K words in WSJ section 19. We use this supertagger to supertag section 15-18 and sec- tion 20. We train an NP Chunker on section 15-18 with fast TBL, and ... cope with much more ambiguities due the large size of the supertag set. The results are shown in Table 2. We test on both normalized and unnormalized models with both hand coded s...
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "Adaptivity in Question Answering with User Modelling and a Dialogue Interface" pptx
... sentences) and produce the final answer accordingly, e.g.: — System: Roald Dahl wrote many books for kids and adults, including: “The Witches”, “Charlie and the Chocolate Fac- tory”, and “James and the ... interest/bookmarks, w. Analogies can be found with the SeAn (Ardissono et al., 2001) and SiteIF (Magnini and Strapparava, 2001) news recommender systems where age and brows...
Ngày tải lên: 17/03/2014, 22:20