Báo cáo khoa học: "Segmented and unsegmented dialogue-act annotation with statistical dialogue models∗" ppt

... July 2006. c 2006 Association for Computational Linguistics Segmented and unsegmented dialogue- act annotation with statistical dialogue models ∗ Carlos D. Mart ´ ınez Hinarejos, Ram ´ on Granell, ... where the dialogue structure could be completely different, and it requires the definition of new rules. Similar to other NLP problems (like speech recognition and understan...

Ngày tải lên: 08/03/2014, 02:21

... factual and opinionated ques- tions for each language and also the Gold Standard for their answers in the corpus. The purpose of our work is to study the challenges involved in a mixed fact and ... growing in parallel with the evolution of the Social Web. This pa- per presents two corpora of blog posts in Eng- lish and in Spanish, annotated according to the EmotiBlog annotation...

Ngày tải lên: 20/02/2014, 09:20

... equipped with an automatic sample injector. The column was equilibrated at room temperature in 50 m M sodium phosphate, pH 7.0, and calibrated with gel-filtration standards from Biorad and Sigma. ... domains (SKA, SKB and SKC) and a fragment consisting of SK domains B and C (SKBC) at pH 7.0. The data for SKA at pH 7.0 and 0.88 mgÆmL )1 have been taken from Azuaga et al. [19]. F...

Ngày tải lên: 21/02/2014, 03:20

... pairwise similarity of A and C, B and F, G and H obtained by BLEU score is confirmed. Furthermore, a close similarity between E and F is indicated. G and H (electricity and physics, respectively) ... filed in different countries and are connected through the patent family id. We extracted 172,472 patents that were both filed with the USPTO and the EPO and contain an English...

Ngày tải lên: 22/02/2014, 03:20

... size and shape of the substrate and second, incorporation of an imido-group increases the stability of selenolate in the catalytic cycle. More efficient antioxidant ability compared with 6-SeCD and Ebselen ... substrate binding compared with Ebselen [15]. When the sub- strates were H 2 O 2 , t-BuOOH and CumOOH, we found that the GPX activities with 6-CySeCD for the reduc- tion of...

Ngày tải lên: 19/02/2014, 02:20

... c k ’s lift and right siblings, CFG rewrite rule that expands c k and c k ’s parent (from (Ding and Chang, 2008)). 3.2 New Word Features We introduce some new features which can be extracted without ... information of sub-trees in a given parse. With help of these new features, our sys- tem achieves 93.49 F-measure with hand-crafted parses. Comparison with the best reported result...

Ngày tải lên: 20/02/2014, 04:20

... concatenative morphology (affixes and stems) and templatic morphology (root and patterns). There is a va- riety of morphological and phonological adjust- ments that appear in word orthography and inter- act with orthographic ... samples, while D2 and TB got max BLEU score in 2.2% and 0.1% of samples, respectively. The difference between ROC and D2 and ATB is statistically s...

Ngày tải lên: 20/02/2014, 11:21

... dashed line between 3 and b links the main verbs both in the texts T 1 and T 3 and in the hy- potheses H 1 and H 3 . After substituting 3 with b and 2 with a , we can detect if T 1 and T 3 share the ... rows report the cross-pair similarity carried out with Eq. 6 with (Synt Trees with placeholders) and without (Only Synt Trees) augmenting the trees with placehold- er...

Ngày tải lên: 20/02/2014, 12:20

... Co-training for Predicting Emotions with Spoken Dialogue Data Beatriz Maeireizo and Diane Litman and Rebecca Hwa Department of Computer Science University of Pittsburgh ... automatically predicts and adapts to the student’s emotions. ITSPOKE uses supervised learning to predict emotions with spoken dialogue data. Al- though a large set of dialogues have been collected, ......

Ngày tải lên: 20/02/2014, 16:20

... matrix with and with since both and contain negative values and are not prob- ability distributions. However, using equations 3 and 4, we can attach a probabilistic interpretation to LSA, and then ... (Hofmann, 1999) is a generative statistical latent class model: (1) select a document with probability (2) pick a latent class with probability and (3) generate a word wit...

Ngày tải lên: 22/02/2014, 02:20