Báo cáo khoa học: "A speech interface for open-domain question-answering" doc

... general information about the system’s components, a description and time- stamp for each system event and user event, names and timestamps for the system-recorded sound files, and timestamps for ... agreed with the former and 25% for the latter. However, in the open-ended interview, users mentioned handwrit- ing as an important back-up input choice for cases when the speech...

Ngày tải lên: 20/02/2014, 12:20

... with a speech repair identify- ing language model to handle speech repairs, editing terms, and two speakers. Section 2 details the allowable forms of collaboration, interruption, and speech ... take the ban- um the oranges, three constituents would be produced, one for urn, another for take the ban-, and a third for take the oranges. Another complicating factor of dialog i...

Ngày tải lên: 20/02/2014, 19:20

... acoustic-prosodic cues for repair processing. Discussion In this paper, we have presented a" ;speech- first" model, the Repair Interval Model, for studying repairs in spon- taneous speech. This ... Disfluencies in spontaneous speech pose serious prob- lems for spoken language systems. First, a speaker may produce a partial word or FRAGMENT, a string of phonemes that...

Ngày tải lên: 20/02/2014, 21:20

... incu- bated for 4 days with each of the peptides (10 lm), and cells were fixed and used for immunocytochemical analyses. Immunocytochemistry Neurons were fixed in 4% paraformaldehyde for 20 min at ... to transformed Ca 2+ -competent E. coli cells (ER2566) by heat shock. The transformed cells were spread on LB agar plates containing ampicillin (50 mgÆL )1 ), single colonies were picked fo...

Ngày tải lên: 18/02/2014, 13:20

... labelled information for training. Our sys- tem extracts transliteration pairs in an unsupervised fashion. It is also able to utilize labelled information if available, obtaining improved performance. We ... of the Association for Computational Linguistics, pages 469–477, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics A Statistical Model for...

Ngày tải lên: 19/02/2014, 19:20

... p null = 10 −10 for this value in the experiments we report below. 784 either φ P z i for phrase pairs or φ null for single lan- guage phrases. We choose Dirichlet process (DP) priors for these parameters: φ P z i ∼ ... proce- dure for each sentence pair is non-trivial, prov- ing NP-complete for learning phrase based models (DeNero and Klein, 2008) or a high order poly- nomial (O(...

Ngày tải lên: 20/02/2014, 07:20

... named entities, as well as additional in- formation such as part-of -speech tags and merging these information into markables that are the start- ing point for the mentions used by the coreference resolution ... standoff format of the MMAX2 annotation tool (M ¨ uller and Strube, 2006) with MiniDiscourse, a library that efficiently imple- ments a subset of MMAX2’s functions. Using a generic...

Ngày tải lên: 20/02/2014, 09:20

... allows that use of future information in ad- dition to past information. The pipeline model nat- urally allows access to all the past information. Algorithm 3 Pseudo code for the look ahead algo- rithm. ... rightmost S action taken before a non-S action happens. Note that it is possible that there is a relation between a and b, but we can- not perform R or L now. Therefore, we should consid...

Ngày tải lên: 20/02/2014, 12:20

... only for N’s small enough to yield non-zero P(n) scores. For test corpora of reasonable size, the metrics are usually well-defined for N≤4. The BLEU proposed by Papineni et al. (2002) for ... recall scores for increasingly longer n-grams. For test corpora of reasonable size, the metrics are usually well- defined for N≤4. The ROUGE metric proposed by Lin and Hovy (2003)...

Ngày tải lên: 20/02/2014, 16:20

... acquire more over time: we in- tend for it to generalize and encapsulate best practices, and serve as a testbed for new practices. Dyna is now be- ing used for parsing, machine translation, morphological analysis, ... probabilities, which permits heuristic early stopping before the agenda is empty. With viterbi values, it amounts to uniform-cost search for the best parse, and an item’...

Ngày tải lên: 20/02/2014, 16:20