utterances in realtime spoken

Ngày tải lên: 17/03/2014, 07:20

... rules from the train- ing text. The DR-DA matrix is created after cluster- ing the sentences into different dialogue acts (DAs), counting the occurrences the DRs in DA, and intro- ducing an entropy-based ... Manning. 2003. Is it harder to parse chinese, or the chinese treebank? In Proc. Annual Meeting of ACL, pages 439–446. A. Stolcke. 2002. Srilm - an extensible language model- ing toolkit. In Proc. ... and Information Engineering National Cheng Kung University Tainan, Taiwan 1 liangnet@gmail.com 2 chunghsienwu@gmail.com Chia-Ping Chen Department of Computer Science and Engineering National Sun...

Ngày tải lên: 20/02/2014, 05:20

... model was esti- mated by transcribing 50 randomly chosen dialogs from the training set in Section 4.2 and calculat- ing the frequency with which the ASR engine rec- ognized ˜ A t such that ˜ A t = ... this way, we were able to create synthetic training sets of varying sizes, as well as a test set of 1000 dialogs. Each generated dialog d in each training/test set consisted of a sequence of values ... distributions in our model are multinomials. Hence θ is a vec- tor that parameterizes the user model according to Pr(A t = a | S t = s, U t = u; θ) = θ asu . The problem we are interested in is estimating...

Ngày tải lên: 20/02/2014, 09:20

Ngày tải lên: 23/03/2014, 17:20

Ngày tải lên: 22/06/2014, 23:20

Ngày tải lên: 18/03/2014, 02:20

Ngày tải lên: 23/03/2014, 18:20

... convinced that computer scientists, engineers, and others who work in the area of spoken multimodal dialogue systems, no matter if in academia or in industry, may find the volume interesting ... at Tokyo Institute of Technology (TIT), Japan. He received the ME degree in Information Science and Engineering from TIT in 2002. His research interests are speech information processing, especially ... work. XI Introduction Spoken multimodal human-computer interfaces constitute an emerging topic of interest not only to academia but also to industry. The ongoing migra- tion of computing and information...

Ngày tải lên: 17/02/2014, 20:20

... result, the instruction did not match the initial essay quality. Nonetheless, in the open- question interviews, many users indicated using the NM as a reference while updating their essay. In addition ... B. Clark and S. Peters. 2006. Responding to Student Uncertainty in Spoken Tutorial Dialogue Systems. International Journal of Artificial Intelligence in Education, 16. C. Rich and C. L. Sidner. ... Q14-16 were included to probe user’s post tutoring perceptions. We find a trend that in the NM problems it was easier for users to under- stand the system’s main point (Q14). However, in terms...

Ngày tải lên: 20/02/2014, 12:20

... by conducting experiments using our learner corpus, which contains information on learners’ errors. 1 Introduction One of the most important things in keeping up with our current information-driven ... their root forms, three combinations of these (one preceding word and one following word/two preceding words and one following word/one preceding word and two following words), and the first ... automatically. In this paper, we introduce a method of detect- ing learners’ errors, and we examine to what ex- tent this could be accomplished using our learner corpus data including error tags...

Ngày tải lên: 20/02/2014, 16:20

... found in a writ- ten text. extended in order to maintain a coherent discourse structure for the modelling of the producer. Thus rhetorical relations describing planning processes are introduced. ... directed planning process on the part of the producer. In order to obtain a better understand- ing of the planning process we analyse spoken dis- course elicited in an experimental setting. Subjects ... remaining part of the paper is organised as follows. Section 2 contains a description of the ex- perimental setting in which the example discourse was obtained (Habel and Tappe, forthcoming)....

Ngày tải lên: 20/02/2014, 18:20

... although understandable in the context of informing work on spoken dialogue systems, is somewhat at odds with previous think- ing about turn-taking. Although turn-taking behaviour is cul- turally ... below 400ms, and increasing the thresh- old value in increments of 100ms. Table 2 shows the values for the highest perform- ing models. The model that only inserts continuers in pauses over 900 ... CHI Conference on Human Factors in Computing Systems. V.H. Yngve. 1970. On getting a word in edgewise. In Pa- pers from the Sixth Regional Meeting, Chicago Linguistic Society, pages 567-577. 58 ...

Ngày tải lên: 22/02/2014, 02:20

... Identifying non-referential it: a machine learning approach incor- porating linguistically motivated patterns. In Proceed- ings of the ACL Workshop on Feature Selection for Ma- chine Learning in NLP, Ann Arbor, ... Satou (2004). Improv- ing the identification of non-anaphoric it using Support Vector Machines. In International Joint Workshop on Natural Language Processing in Biomedicine and its Applications, ... which is frequent in spoken language, but rare in written text. It covers instances of it which are indeed ref- erential, but whose referent is not an identifiable linguistic string in the context...

Ngày tải lên: 22/02/2014, 02:20

... of interest for any rational user. All dominant options represent some tradeoff, but depending on the user’s interest, some of them are more interest- ing tradeoffs than others. Pruning dominated ... for cooperative response generation in information dialogues. In AAAI/IAAI 1999 pp. 148–155. M. Steedman 2000. Information structure and the syntax- phonology interface. In Linguistic Inquiry, 31(4): 649– 689. A. ... group-average clustering. The algorithm begins by assigning each unique attribute value to its own bin, and suc- cessively merging adjacent bins whenever the dif- ference between the means of the bins falls...

Ngày tải lên: 22/02/2014, 02:20

... words in spoken and written corpus, in order to examine whether there are any register variations. Chapter 7 will present the conclusions of this study. 1. 4 Main Findings The main findings of ... gnarring sound. g. The wild not … of the bullfinch … is a most jarring and disagreeable noise. h. Through the plashing streets. i. Attended with pricking pains in the right side. j. The rapid increase ... but it marks nominal crash as “following (i.e. being associated with) verbal crash. ” In a simple search of entries including onomatop* in etymologies, only verbal crash was found. In this study,...

Ngày tải lên: 24/02/2014, 18:20

... by including insertion, substitution and reordering, and incorpo- rates grammar rules. In speech domain, (Clarke and Lapata, 2008) investigates sentence compression in broadcast news using an integer ... whether In this study we investigate sentence compres- sion of spoken utterances in order to remove re- dundant or unnecessary words while trying to pre- serve the information in the original sentence. ... n-best parsing and maxent discriminative rerank- ing. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pages 173–180, Stroudsburg, PA, USA. Proceedings of...

Ngày tải lên: 07/03/2014, 18:20

... paper we examine novel types of entrain- ment in two corpora—Switchboard and the Columbia Games corpus. We examine en- trainment in use of high-frequency words (the most common words in the corpus), ... had a high inclination for empathy (understanding the point of view of the other) entrained to a greater extent than others. Reitter et al. (2007) also found that degree of entrainment in lexical ... correlates with task success and minimal interruptions—important goals of SDS. In future work we will explore the consequences of system entrainment to SDS users in helping systems achieve these goals,...

Ngày tải lên: 08/03/2014, 01:20

... requires joint expertise in natural language processing and speech recognition, and best practices in language engineering for every new domain. On the other hand, a statistical learning approach ... Main Conference Poster Sessions, pages 882–889, Sydney, July 2006. c 2006 Association for Computational Linguistics Combining Statistical and Knowledge-based Spoken Language Understanding in ... model training, which is seldom available in practical applications outside of large research labs. A generative HMM/CFG composite model, which integrates easy-to- obtain domain knowledge into...

Ngày tải lên: 08/03/2014, 02:21

... accurate information obtained by the machine (Higashinaka et al., 2004), the more possibility to finish the dialogue task. Practical use of speech act theories in spoken lan- guage processing (Stolcke ... evaluat- ing spoken dialogue agents. In Proceedings of the ACL, 271–280 M. Walker and R. Passonneau. 2001. DATE: a dia- logue act tagging scheme for evaluation of spoken dialogue systems. In ... investigated. Three main services: registration information service, clinic information service, and FAQ information service are used. This system mainly provides the function of on- line registration....

Ngày tải lên: 08/03/2014, 02:21

... Computing Meaning, volume 3. Kluwer. Raquel Fern´andez, Jonathan Ginzburg, and Shalom Lappin. 2004b. Classifying ellipsis in dialogue: A machine learn- ing approach. In Proceedings of COLING 2004, ... with training a model using a base- line set of features, and then add each remaining feature individually, recording the gain (w.r.t. the f- measure (f (0.5), to be precise)), and choosing the best-performing ... base- line (verb in β yes/no, and length of β) already has some success in identifying fragments, but adding the remaining features still boosts the performance. Having available the string (condition...

Ngày tải lên: 08/03/2014, 04:22