Báo cáo khoa học: "Supervised and Unsupervised Learning for Sentence Compression" ppt

... sentence pairs. Thirty-two of these sentences were used for the human judgments in Knight and Marcu’s ex- periment, and the same sentences were used for our human judgments. The rest of the sentences were ... short and useful summaries. This task is called sentence compression. While several methods have been proposed for sentence compression (Witbrock and Mittal, 1999; Ji...

Ngày tải lên: 20/02/2014, 12:20

... devel- opment calls for information extraction systems which are as retctrgetable and general as possi- ble. Here, we describe SRV, a learning archi- tecture for information extraction ... which is de- signed for maximum generality and flexibility. SRV can exploit domain-specific information, including linguistic syntax and lexical informa- tion, in the form of featur...

Ngày tải lên: 08/03/2014, 05:21

... certain sentences may result in incoherence and information loss. The deletion of certain words and phrases may also lead to ungram- maticality and information loss. The mayor is now looking for ... sen- tences can be expanded into longer ones by inserting and expanding syntactic constituents (and words). Since our constituent-expand stochastic operation simply reimplements Knight...

Ngày tải lên: 08/03/2014, 07:20

... proposed for cenprosin, the AP from Centaurea calcitrapa [30] and for recombinant oryzasin 1, the rice AP [29]. A slightly different picture has emerged for prophytepsin. Using metabolic labeling and ... prophytepsin, the precursor form of barley AP containing the prosegment and the PSI (PDB code: 1QDM) [25] (Fig. 2). Both APs are two-chain polypeptides in their mature forms and...

Ngày tải lên: 19/02/2014, 12:20

... correct destination (and orienta- tion in the single -sentence version). We follow the same evaluation scheme as Chen and Mooney and perform leave-one-map-out exper- iments. For the first task, we ... data, and test on sen- tences from the third, unseen map. For all comparisons to the Chen and Mooney re- sults, we use the performance of their refined land- marks plans system which...

Ngày tải lên: 19/02/2014, 19:20

... tagger NE-AL and for the parser PARSE-AL. Further, random selection and extrinsic selection perform worst. Most importantly, both MTAL pro- tocols clearly outperform extrinsic and random se- lection ... 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 inf...

Ngày tải lên: 20/02/2014, 09:20

... “<crisis- handling committee> 8 ” as an organization name in preference to the alternative name candidate “<crisis-handling> 8 ”. For a name candidate, high-confidence infor- mation ... event) and a set of arguments. When a name candidate is in- volved in an event, the trigger word and other arguments of the event can help to determine the name boundaries. For example...

Ngày tải lên: 20/02/2014, 12:20

... transfer is as simple and straightfor- ward as possible. On the other hand, they need to encode sufficiently fine-grained information to steer transfer. Furthermore, target and source representations ... over feature structures for transfer, see (Emele and Dorna, 1998). 2For presentational purposes we leave out morpho- syntactic information in f-structures here and in the...

Ngày tải lên: 20/02/2014, 18:20

... structures for rela- tional learning from questions and answers. We designed sequence kernels for words and Part of Speech Tags which capture basic lexical seman- tics and basic syntactic information. ... (Collins and Duffy, 2002; Kudo and Matsumoto, 2003; Cumby and Roth, 2003; Shen et al., 2003; Moschitti and Bejan, 2004; Culotta and Sorensen, 2004; Kudo et al., 2005; T...

Ngày tải lên: 22/02/2014, 02:20

... monomer. Monomers A (green) and B (yellow) form dimer 1, while monomers C (red) and D (blue) form dimer 2. L5 ⁄ 7, the loop between b-strands 5 and 7 which contains b-strand 6; N term, amino terminus ... dimers, with mono- mers A and B in dimer 1 and C and D in dimer 2 (Fig. 8). The a-crystallin domain of each monomer is composed of nine b-strands (labeled b2–b10), with the b6 str...

Ngày tải lên: 07/03/2014, 12:20