Báo cáo khoa học: "TENSE GENERATION IN AN INTELLIGENT TUTOR FOR FOREIGN LANGUAGE TEACHING: SOME ISSUES IN THE DESIGN OF THE VERB EXPERT" pot

... TENSE GENERATION IN AN INTELLIGENT TUTOR FOR FOREIGN LANGUAGE TEACHING: SOME ISSUES IN THE DESIGN OF THE VERB EXPERT Danilo FUM (*), Paolo Giangrandi(°), Carlo Tasso (o) ... techniques for developing very sophisticated systems, called Intelligent Tutoring Systems, in the specific domain of foreign language teaching (Barchan, Woodmansee, and Yazdani, 1985; Cunningham, ... main capabilities. The final section deals with the relevance of the present proposal both in the framework of linguistic studies on verb generation and of intelligent tutoring systems for...

Báo cáo khoa học: "INTEGRATING TEACHING THE ENGLISH TENSE: NAIVE AND FORMAL GRAMMARS IN AN INTELLIGENT TUTOR FOR FOREIGN LANGUAGE TEACHING" pdf

... with in order to build an intelligent tutoring system (ITS) in the domain of foreign language teaching is that of establishing what kind of grammatical knowledge has to be included in the ... choice and conjugation of an English verb tense. One of the main concerns in designing the knowledge base for this module has been that of maintaining the wealth of ideas and intuitions existing ... • ~ • TEACHING THE ENGLISH TENSE: INTEGRATING NAIVE AND FORMAL GRAMMARS IN AN INTELLIGENT TUTOR FOR FOREIGN LANGUAGE TEACHING Danilo Fum 1, Bruno Pani 2 and Carlo Tasso 2 1 Dipartimento...

Tài liệu Báo cáo khoa học: "ModelTalker Voice Recorder – An Interface System for Recording a Corpus of Speech for Synthesis" ppt

... synthesis. In this type of synthesis, units of recorded speech are appended. By using recorded speech, many of the voice qualities of the person recording the speech remain in the resulting synthetic ... recordings. The system’s intention is to make the process of recording a corpus of ut-terances relatively easy for those inexpe-rienced in linguistic analysis. Ultimately, the recorded corpus and the ... prove useful for other purposes as well. The system facili-tates the recording and labeling of large cor-pora of speech, making it useful for speech and linguistic research, and it provides...

Báo cáo khoa học: "Talking through procedures: An intelligent Space Station procedure assistant" pot

... substan-tial input from astronauts, trainers, engineers, andother NASA personnel. The first version of the system operated on a simplified (and invented)procedure for unpacking and operating ... Parsing and interpretation The output of the speech recognizer is parsedusing SRI' s Gemini parser. The text of the rec-ognized speech and the resulting parse are thenfed to Alterf (Rayner and ... Dialogue Input ManagementEach behavior agent has an agenda (Rudnickyand Xu 1999) of the types of input it is expecting. The behavior agents are maintained in a priorityqueue according to recency of...

Báo cáo khoa học: "GENERALIZED CHART ALGORITHM: AN EFFICIENT PROCEDURE FOR COST-BASED ABDUCTION ATR" ppt

... i.e., the number of derivation steps in TD and HD, and the number of passive and active edges in GCF and GCO. The decimals in parentheses show the ratio of the performance of each method to the ... lexicons are the words in the input string, each of which is used as the index for a subset of the edges in the chart; each edge incident from (the start-point of) lexicon w represents the sub- ... cost-based abduction. Introduction Spoken language understanding is one of the most challenging research areas in natural language pro- cessing. Since spoken language is incomplete in var- ious ways,...

Báo cáo khoa học: "Exploiting Comparable Corpora and Bilingual Dictionaries for Cross-Language Text Categorization" potx

... sense-indexing to inducea second-order similarity for the other terms in the lexicons. We evaluate the performance of the cross-lingual text categorization, using both the BoW Kernel and the Multilingual ... do-main kernel. We can observe that the latter largelyoutperform a standard BoW approach. Analyzing the learning curves, it is worth noting that when the quantity of training increases, the performancebecomes ... of tjis the frequency of wz in tj. The similarity among two texts in the VSM is then estimated by computing the cosine of their vectors in the VSM.Unfortunately, such a model cannot be adoptedin...

Báo cáo khoa học: "Scaling to Very Very Large Corpora for Natural Language Disambiguation" potx

... number of samples has been annotated for training. However, we see that the larger the pool of candidate instances for annotation is, the better the resulting accuracy. By increasing the pool of ... We can use bagging (Breiman, 1996), a technique for generating a committee of classifiers, to assess the label uncertainty of a potential training instance. With bagging, a variant of the ... choose the most uncertain instances for human annotation, with unsupervised learning we want to choose the instances that have the highest probability of being correct for automatic labeling and...

Báo cáo khoa học: "A Study on Richer Syntactic Dependencies for Structured Language Modeling" ppt

... oneway of conditioning the probabilities is by annotat-ing the extra conditioning information onto the nodelabels in the parse tree. We can annotate the trainingcorpus with richer information and ... both the LP and the LRdropped after 3 training iterations: the N-best EMvariant used for SLM training algorithm increases the likelihood of the training data, but it cannot guar-antee an increase ... the three enrichment schemes described in Sec-tion 3 and their combinations, we evaluated the PPLperformance of the resulting seven models on the UPenn Treebank and the WER performance on the WSJ...

Tài liệu Báo cáo khoa học: "Multimodal Generation in the COMIC Dialogue System" docx

... the fission module needs the timing in- formation from the speech synthesiser to finalise the schedules for the other modalities, the synthesiserfirst prepares and stores the waveform for its inputtext; ... Steedman’s (Steedman, 2000a) theory of information structure and intonation is used to con-strain the choice of pitch accents and boundary tones for the speech synthesiser.5 Speech Synthesis The ... by selecting and structuring content, planning the surface form of the text to realise that content,choosing multimodal behaviours to accompany the text, and controlling the output of the whole...

Báo cáo khoa học: "Response Generation in Collaborative Negotiation*" pdf

... Belief and Discourse Levels for (2) and (3) threshold, the evaluator has insufficient information to determine whether to adopt _bel and therefore will ini- tiate an information-sharing subdialogue ... belief and the evidence provided to her and adopt the belief if the evidence is convincing. On the other hand, if the evalua- tion indicates that the agent should maintain her original belief, ... execution, the problem-solving level which contains the actions being performed to construct the do- n~n plan, the belief level which consists of the mutual beliefs pursued during the planning...

Xem thêm