Báo cáo khoa học: "Undestanding Stories in Different Languages with GETA-RUN" doc

Ngày tải lên: 09/03/2014, 01:20

... P-N. It is intriguing that the machine learning systems have roughly equal dif- ficulty in separating sarcastic tweets from positive tweets and from negative tweets. These results indicate that ... still in its infan- cy. One reason for the lack of computational mod- els has been the absence of accurately-labeled naturally occurring utterances that can be used to train machine learni...

Ngày tải lên: 20/02/2014, 05:20

... corpus being smaller and having an infrequent number of “Excellent” and “Poor” stories, as shown in Table 1. In the “Thief” corpus the learner simply col- lapses most stories into “Good,” resulting in ... texts ac- cording to plot quality and produce advice in an interactive learning environment in- tended to help students with story writing. We focus on the story rewriting tas...

Ngày tải lên: 20/02/2014, 12:20

... modality-independent. For example, the in- put in Figure 2 could equally well have been the user simply pointing to a design on the screen, with no speech at all. This would have resulted in the ... The same princi- ple holds for error handling, which is implemented at different levels in our approach. In the guided-browsing phase of the COMIC sys- tem, the user may browse tilin...

Ngày tải lên: 20/02/2014, 15:20

... course. Counter-training provides a framework in which other recognizers, training in parallel with a given recognizer , can label documents as belonging to their own, other categories, and therefore as being less ... 1998). In co-training, learning centers on labeling a set of data-points in situations where these data-points have multiple disjoint and redun- dant views. 8 Examples...

Ngày tải lên: 20/02/2014, 16:20

... occurring in a hand-cleaned sub-corpus, as well as linguistic intuition. Using this method, Kveain and Oliva (2002) report find- ing 2661 errors in the NEGRA corpus (containing 396,309 tokens). Interestingly, ... work Considering the significant effort that has been put into obtaining pos-tagged reference corpora in the past decade, there are surprisingly few pub- lications on the issue...

Ngày tải lên: 22/02/2014, 02:20

... linguistic features would allow gen- uinely novel entries to be created, which, given that the user is a non-linguist, Would almost certainly lead to inconsistencies. In addition, endowing ... variable and indeterminate, they are much less so than judgments of semantic acceptabil- ity, which do not play any part in VEX's main decision-making process. In or- der to remind th...

Ngày tải lên: 22/02/2014, 10:20

... a cause of inefficiency in processing. Second, prepositions may have sev- eral distinct, if related, meanings. (This problem becomes even more acute in a multilingual set- ting with a common ... system The ontological types of InL indices are formalized by dividing the set of InL variables into sorts. Tak- ing results from work in automated theorem prov- ing (Cohn 1984, Walthe...

Ngày tải lên: 22/02/2014, 10:20

... principles of reasoning with uncertainty: e.g. Connoly (1994) and Mitkov (1997). Our system can be included into the first approach. In these integrated approaches the semantic and domain ... with discourse anaphora in unrestricted texts with partial parsing. It is based on the process of parsing described in Figure 3. So this process will take the output of a POS tagging...

Ngày tải lên: 08/03/2014, 05:21

... is involved in defense against transposones and viruses [31–33]. However, there are some problems with inhibition of viral infections with RNAi. To escape RNAi-mediated A 23 85 B C Fig. 3. Inhibition ... TMV infection in plants inoculated with TMV, catalytic RNA and Pb 2+ , respectively, as shown in the table, was analyzed using RNA templates isolated from tobacco leaves and prime...

Ngày tải lên: 16/03/2014, 12:20