Báo cáo khoa học: "Scaling up from Dialogue to Multilogue: some principles and benchmarks" doc

... Linguistics Scaling up from Dialogue to Multilogue: some principles and benchmarks Jonathan Ginzburg and Raquel Fern ´ andez Dept of Computer Science King’s College, London The Strand, London WC2R ... consider how to scale up dialogue proto- cols to multilogue, settings with multiple conversation- alists. We have extracted two benchmarks, MLDSA and MAG, to evalua...

Ngày tải lên: 08/03/2014, 04:22

... preprocessing for automatic align- ment, the datasets were tokenised and lowercased and only sen- tence pairs corresponding to a one -to- one sentence alignment with lengths ranging from one to 40 tokens on ... an- notation. We use the automatic dependency conver- sion of the French Treebank into dependency format provided to us by Candito and Crabb ´ e and described in Candit...

Ngày tải lên: 20/02/2014, 04:20

Ngày tải lên: 08/03/2014, 01:20

... present in the cytosol fraction (caspase-2, -3, -6, -7, -8 and -9) of living cells to separate silent precursor caspases in the cytosol from pro-apoptotic cofactors in the mitochondria and nucleus ... Ser112 and Ser136, Bad is dephospho- rylated at Ser155, which allows translocation to mitochondria and the binding of Bcl-xL [86], and increases the release of cytochrome c from...

Ngày tải lên: 14/02/2014, 22:20

... distributed random vari- able, with mean equal to the population mean, and variance to be estimated by the model. Stated dif- ferently, a random effect allows us to add a factor to the model ... disfluency and the position of a word relative to it. Non-final repetitions and words next to fragments have an IWER up to 15% (absolute) higher than the average word, while fi- nal...

Ngày tải lên: 20/02/2014, 09:20

... for example to smooth the dialogue flow, i.e. to bet- ter explain the dialogue situation to the user or to make the response more conversational. The wiz- ard can select a prompt from a predefined ... actions are logged and afterwards used to help automate the correct behavior of the system and to increase the overall performance. 3 Collecting natural language data In orde...

Ngày tải lên: 20/02/2014, 12:20

... model (Smith and Eisner, 2005), up to 14 percentage points better than MLE. We find improvements both when training from data alone, and using a tagging dictionary. 1 Introduction Unsupervised learning ... models have been used to find classes that can improve smoothing and reduce perplexity (Brown et al., 1992; Saul and Pereira, 1997). Unfor- tunately, due to a lack of standa...

Ngày tải lên: 20/02/2014, 12:20

... also identified: proteins 7a and 11 correspond to the endo- cellulases Cel5D [30] and Cel5A [31], respectively, and protein 8 corresponds to the carboxymethyl cellulase Cel5N [14], and protein 4, in which ... case of cell- ulosomes from C. cellulovorans may be partly due to the existence of various categories of cohesins and dockerins which determine the composition of the ce...

Ngày tải lên: 18/02/2014, 08:20

... textual dialogue. The results point to ways in which dialogue systems can effectively lever- age affective channels to improve dialogue act classification. 1 Introduction Dialogue systems aim to ... ex- perimenting with lexical and prosodic features, and applying the dialogue act model as a constraint to aid in automatic speech recognition (Stolcke et al., 2000). I...

Ngày tải lên: 20/02/2014, 04:20

... overlay (Alexandersson and Becker, 2001). 4 Related Work and Novel Aspects Many dialogue systems deployed today follow a state-based approach that explicitly models the full (finite) set of dialogue ... evaluation, situation, and resource. These are used to model problem-solving at a domain-independent level and are taken as arguments by all update opera- tors of the dialogue m...

Ngày tải lên: 20/02/2014, 12:20