Báo cáo khoa học: " LOCAL AND GLOBAL STRUCTURES IN DISCOURSE UNDERSTANDING" docx

... Helsinki, Fabianlnkatu 33, 00170 Helsinki 17, Finland.) I INTRODUCTION We are interested in the nature of content structures in terms of which it would be possible to account for reasoning ... reflect intuitive attention, interest and judgment processes of the understander that occur during reading a text, on the other. They should be usable in interpreting very different...

Ngày tải lên: 18/03/2014, 02:20

... concept based on the counts in P (t|m). 4.5 Linker and Ranker Training We train the coefficients for the ranker features us- ing a linear Ranking Support Vector Machine, using training data gathered from ... Wikipedia links are considered gold-standard links for the training process. The methods for compiling the Wikipedia training corpus are given in Section 5. We train the linker as a...

Ngày tải lên: 17/03/2014, 00:20

... intertranslatable (Niehren and Koller, 1998) if binding and linking relations in A -structures are ignored. For the interaction of binding with parallelism we follow the basic idea that binding relations ... constraints for immediate dominance and labeling X:f(X1, , Xn), (e.g. X1:@(X2,)(3) and X3:lam(X4) etc.) and bind- ing constraints A(X)=Y. It is convenient to dis-...

Ngày tải lên: 20/02/2014, 18:20

... error rate training In contrast to task pooling and task mixtures, the specific setting addressed by multi-task minimum error rate training is one in which the generative train test pooling mixture A-C ... pooling data from separate tasks into a single training set. Instead of a trivial enlargement of training data by pooling, we train the pooled models on the same amount of sentences as...

Ngày tải lên: 22/02/2014, 03:20

... type i. We next include a normalization step in which each row in each of L * and R * is scaled to unit length, yielding matrices L ** and R ** . Finally, we form a single descriptor matrix ... r 2 = 300, and we again normalize the descriptors to unit length, yielding a new pair of latent descriptor matrices L ** and R ** . Finally, we concatenate L ** and R ** into a s...

Ngày tải lên: 07/03/2014, 22:20

... not taken into account in the final grading of the systems. The overall ranking for all systems (excluding the TECH corpus results) is given in Figure 2, in terms of the Sent and Char F-measures. ... and Kenneth W. Church. 1991. A Program for Aligning Sentences in Bilin- gual Corpora. In 29th Annual Meeting of the Association -for Computational Linguis- tics, Berkele...

Ngày tải lên: 08/03/2014, 05:21

... between Mandarin Chinese and Cantonese, and report work in progress for dealing with homophones and tonal patterns despite potential skewed distributions of indi- vidual Chinese characters in the ... Virga and Khudanpur, 2003). Direct orthographic mapping (e.g. Li et al., 2004), mak- ing use of individual Chinese graphemes, tends 1 Mandarin names are transcribed in Hanyu...

Ngày tải lên: 17/03/2014, 02:20

... designed for perspicuous handling of linguistic data. Data management was done record by record to maintain integrity, but the normal form constraints on at- omicity and singularity of fields were ... contains fields for various aspects of the form, meaning, meaning-to-form mapping, and use of that sense. For the update and retrieval operations defined on relations to work right...

Ngày tải lên: 17/03/2014, 19:21

... neuroglobin and cytoglobin in a situation of chronic hypoxia in mice were examined using real-time quantitative PCR. The kinetics of the hypoxic expression of neuroglobin (brain, eyes) and cytoglobin ... neuronal (brain and retina) and some endocrine tissues, whereas Cygb is detected in the nucleus and in the cytoplasm of many types of tissue [2,3]. In response to hypoxia,...

Ngày tải lên: 23/03/2014, 09:21

... the same remainder to the right of the dot were collapsed ( and ). Since they are indistinguishable in terms of future behavior, making a distinction results in an unnec- essary increase of the ... to deal with the bracketing structure of compounding, which would be impossible to cover in full generality in the finite-state setting. In languages like German, spelling conventions fo...

Ngày tải lên: 23/03/2014, 19:20