Báo cáo khoa học: "Flexible Guidance Generation using User Model in Spoken Dialogue Systems" pdf

... appropriate user modeling in order to generate cooperative responses to each user in spoken dialogue systems. Un- like previous studies that focus on user s knowledge or typical kinds of users, the user ... Flexible Guidance Generation using User Model in Spoken Dialogue Systems Kazunori Komatani Shinichi Ueno Tatsuya Kawahara Hiroshi G. Okuno Graduate School of...

Ngày tải lên: 31/03/2014, 03:20

... the models de- rived from adding in the DATE metrics. 4.1 Results using Logfile Standard Metrics We applied PARADISE to develop models of user satisfaction using the core metrics; the best model fit ... boosting for modeling user satisfac- tion. Tree models using dialogue act metrics can achieve model fits as high as 48% reduction in error. However, we need to test both these...

Ngày tải lên: 31/03/2014, 04:20

... headline. Jin and Hauptmann (2002) proposed a probabilistic model for headline generation in which they divide head- line generation process into two steps; namely the step of distilling the information ... headline that contains the largest num- ber of the most frequent words in the document taking into account ignoring stop words and giving earlier sentences in documents mo...

Ngày tải lên: 20/02/2014, 05:20

... fine-grained as the models used by de- pendency parsers, but still contains some semantic information beyond unlabelled relations, a com- promise can be made. We show that using linear diagramming models ... the root in G. 3. Determining the root: Using the root- finding process described in (Marneffe et al., 2006), find the root relation ˆ R( ˆ G, ˆ D) ∈ G. 4. Initialize a sentence diag...

Ngày tải lên: 08/03/2014, 01:20

... comparing the produced headlines against one reference headline produced by a human using ROUGE (Lin, 2004). For each input document, we train two language models, using the SRI Language Model ... rebels rebels rebels fighting rebels rebels rebels rebels rebels fighting fighting fighting fighting turkish turkish turkish turkish turkish turkish turkish government government government go...

Ngày tải lên: 23/03/2014, 18:20

... curves for the fol- lowing four combinations of training corpora and method. • TRG: The models were trained using only the real-error corpus (baseline). • SRC: Trained using only the pseudo-error ... (similar to lan- guage models). The mapping features are all binary. The focusing phrase and its two surrounding words of the input are regarded as the window. The mapping features are defined...

Ngày tải lên: 19/02/2014, 19:20

... context setting into the computational one to narrow down the specific meaning of the target, manually realiz- ing this with the help of Roget’s Thesaurus. They defined a lexical chain within Roget’s ... words (λ), is indeed an outside factor which confines the searching scope to the cost of computation and depends on the different applications. If we tuned it using the training data...

Ngày tải lên: 08/03/2014, 02:21

... up, and the cosine between the resulting win- dow vectors is assigned to the gap between the win- dows in the text. High values indicate lexical close- ness. Troughs in the resulting similarity'curve ... Considering the additional effort and resources involved in using context vec- tors, the modest boost in performance might often not be worth the effort in practice. Th...

Ngày tải lên: 17/03/2014, 07:20

... distinction in the subsequent exposition. The overall architecture of the statistical translation approach is summarized in Figure 1. 2 Aligmnent Models A key issue in modeling the string ... performed a training wit.la only 5 000 sentences out of the training corpus. For this training condition, the word error rate went up only slightly, namely from 5.15}. (for 80,000 training...

Ngày tải lên: 17/03/2014, 23:20

... Loper, Szu ting Yi, and Martha Palmer. 2007. Combining lexical resources: Mapping between prop- bank and verbnet. In In Proceedings of the 7th Inter- national Workshop on Computational Linguistics. Yashar ... contains 113K verb instances, 97K of which are verbs represented in at least one VerbNet class. Semlink includes 495 verbs, whose instances are labeled with more than one class (incl...

Ngày tải lên: 23/03/2014, 14:20