Báo cáo khoa học: "Focus to Emphasize Tone Structures for Prosodic Analysis in Spoken Language Generation" pot

... the tone mark L+H* (rising accent tone) instead of H*. The groups of speech acts, that we consider in this paper, include intend- ing (EN0ab), want (DE8b), and victory (KA4a), to explore tone ... posi- tions for accent information. To determine fo- cus information, a speaker’s intentions must be revealed. We apply speech act theory to written sentences, our input, to determin...

Ngày tải lên: 23/03/2014, 18:20

... well-formedness con- straints (Hirschberg, 1993). However, producing all this information – using full parsing, including es- tablishing semanto-syntactic relations, and full dis- course analysis ... decreased, and the amount of training data was increased, so that in the end only the 3 best experiments used all available training data (i.e. the remaining 95%). Increasing the training dat...

Ngày tải lên: 17/03/2014, 06:20

... (Wilson et al., 2005) as the indicators to identify the substructures for the con- volution kernels, and extract different sub -structures according to these indicators for various types of parse ... Neural Information Processing Systems, pages 171–178, Cambridge, MA. MIT Press. Michael Collins and Nigel Duffy. 2001. Convolution kernels for natural language. In Proceedings of Ne...

Ngày tải lên: 30/03/2014, 17:20

... participating Table 1. Amino acid frequencies (%) in a-amylase linkers, in a set of globular proteins, in the Swiss-Prot databank and in intrinsically unstructured proteins. Amino acid Linkers a Globular proteins b Swiss-Prot c Intrinsically unstructured proteins b Ala ... (Table 1). There is therefore a much weaker driving force for folding the connecting linkers when compared with...

Ngày tải lên: 14/02/2014, 18:20

... certain threshold size has been reached. Finally, we introduced a novel technique for in- tegrating feedback from the student answers them- selves into the grading system. Using a method similar to ... assigned to each answer. In the per-assignment setting, each data point is an assignment-student pair created by to- taling the scores given to the student for each ques- tion...

Ngày tải lên: 22/02/2014, 02:20

... been proved to be quite useful for ranking parses in syntactic analysis. For example, Mager- man (1995), Collins (1996), and Charniak (1997) proposed statistical parsing models which incor- porated ... in the training sample is a verb-noun collocation e, which is defined in the formula (1). A verb-noun collocation e can be divided into two parts: one is the verbal part ev...

Ngày tải lên: 08/03/2014, 06:20

... of tree -to- string alignment templates obtained in training In the following, we formally describe how to introduce tree -to- string alignment templates into probabilistic dependencies to model ... test corpus) using the training toolkits publicly released by Philipp Koehn with its default setting. To perform minimum error rate training (Och, 2003) to tune the feature weights to...

Ngày tải lên: 17/03/2014, 04:20

... u'ees for input strings are built bottom-up, while predictions are made top-down prior to parsing. The ACTION/GOTO table is constructed during preprocessing of a grammar and deterministically ... to search through instantiated categories for desired GOTO table entries during parsing. The major innovations of the proposed algorithm include the construction of a minimal siz...

Ngày tải lên: 22/02/2014, 10:20

... Rules G2Wh-I conform to the first principle, according to which lexical categories generally appear as prefixes. Rules G2*b,e-g conform to the second principle, according to which a category ... sister in G2. Finally, rules G2*aii,c,d conform to the fourth principle, according to which a ca- tegory appears as a postfix if it cannot appear as a prefix according co the prec...

Ngày tải lên: 08/03/2014, 18:20

... standard Vector Space Model (VSM) by embedding addi- tional types of information, besides terms, in the representation of documents. An interesting type of information that can be used in such models ... semantic infor- mation from word thesauri like WordNet. Previous attempts to construct GVSM reported contradicting results. The most challenging problem is to incorporate the semantic...

Ngày tải lên: 08/03/2014, 21:20