... avoids such inefficiency, in principle, by allowing each component, to communicate with all other components in the system. However, controlling the flow of information and specifying the interfaces ... has gone into specifying global scheduling heuristics for maintaining an agenda of knowledge sourcc activation records m blackboard system~, and this has sometimes led to treat...
Ngày tải lên: 08/03/2014, 18:20
... training and testing. Figure 1 shows an example of such a sentence. Here, the target word eat evokes the INGESTION frame. Three FEs are present: INGESTOR, INGESTIBLES, and PLACE. 135 Often [an informal ... slot filling information for nouns and adjectives. • The “Other” layer, containing special cases such as null arguments. The semantic entities that we consider in this article are defined...
Ngày tải lên: 08/03/2014, 21:20
Tài liệu Báo cáo khoa học: "Incremental Parsing Models for Dialog Task Structure" doc
... rich clues for building dialog mod- els (Grosz and Sidner, 1986). Dialog models can be built ofine (for dialog mining and summariza- tion), or online (for dialog management). A dialog manager is ... for interpreting user actions in the dialog context, and for generating system actions. Needless to say, a dialog manager operates incrementally as the dialog progresses. In t...
Ngày tải lên: 22/02/2014, 02:20
Tài liệu Báo cáo khoa học: Insights into the structure of plant a-type phospholipase D Susanne Stumpe, Stephan Konig and Renate Ulbrich-Hofmann ¨ ppt
... Pleckstrin (PH) homology domain in the N-terminal region, all the other PLD isoenzymes possess a calcium- and phos- pholipid-binding domain (C2 domain) at the N-ter- minus [5]. From white cabbage, ... present in all members of the PLD superfamily. However, there is low similar- ity in the remaining parts of the molecules. Most mam- malian PLDs contain a PX and a PH domain instead of the...
Ngày tải lên: 19/02/2014, 02:20
Tài liệu Báo cáo khoa học: "Understanding the Semantic Structure of Noun Phrase Queries" pptx
... evolve, it is in- creasingly believed that search will be shifting away from “ten blue links” toward understanding intent and serving objects. This trend has been largely driven by an increasing amount ... according to the label sets defined in Ta- ble 3. There are 1000/496 samples in the train- ing/test set for the Movie domain, 600/366 for the Job domain and 491/185 for the National Pa...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "Learning Hierarchical Translation Structure with Linguistic Annotations" ppt
... points for English to Chinese translation when training on the 400K set. In addition, increasing the size of the training data from 200K to 400K sentence pairs widens the per- formance margin ... latent hierarchical structure, taking advantage of linguistic annotations but shaped and trained for translation. We start by labelling each phrase-pair span in the word-aligned training data w...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "Using adaptor grammars to identify synergies in the unsupervised acquisition of linguistic structure" docx
... shown in Figure 1. In this grammar and the grammars below, under- lining indicates an adapted nonterminal. Phoneme is a nonterminal that expands to each of the 50 dis- tinct phonemes present in ... grammar, in which the subtrees are specified in advance, in an adaptor grammar the subtrees, as well as their probabilities, are learnt from the train- ing data. In order to make parsi...
Ngày tải lên: 20/02/2014, 09:20
Tài liệu Báo cáo khoa học: Complete subunit sequences, structure and evolution of the 6 · 6-mer hemocyanin from the common house centipede, Scutigera coleoptrata pptx
... hemocyanin subunits contain the six copper-coordinating histidines necessary for copper binding (Fig. 3), which are strictly conserved in all arthropod hemocyanins [4,6,38]. No long insertions ... bands contains two distinct polypeptides [14], we determined their N-terminal sequences. In fact both are heterogeneous, but in each case a predominant sequence was obtained: The first 18 amino...
Ngày tải lên: 20/02/2014, 11:20
Tài liệu Báo cáo khoa học: "Optimizing Typed Feature Structure Grammar Parsing through Non-Statistical Indexing" doc
... over positional indexing alone in these ex- periments, attesting to the difficulty of maintaining efficient index keys in an implementation. Positional Path Quick Quick + Indexing Indexing Check Path MERGE ... was trained on a 300-sentence training corpus, as prescribed in (Malouf et al., 2000). The training corpus included 150 sentences also used in testing. The number of paths in pa...
Ngày tải lên: 20/02/2014, 15:21
Tài liệu Báo cáo khoa học: "DEPENDENCIES OF DISCOURSE STRUCTURE ON THE MODALITY" potx
... performed directly. Since most of the utterances in these simple dialogues do not signal the speaker's intent, techniques for inferring intent will be crucial for engaging in spoken task-related ... participated in the experiment on two consecutive days, the first for training and the second for instructing an apprentice. Subjects playing the expert role ware trained by: fo...
Ngày tải lên: 21/02/2014, 20:20