Báo cáo khoa học: "PLANNING FOR PROBLEM IN ADVICE-GIVING FOR MULATION DIALOGUE" pptx

... grouping of sentences containing coordinate conjunctions. Finally, the algorithm is described in Section 3. I GAPPING, RIGHT NODE RAISING AND REDUCED CONJUNCTION I.I Gapping Gapping is ... play. Linguists have described rules for generating Gapping, though none of them has made any effort to formulate a rule for detecting Gapping. (Ross 67b) is the first who suggested a rule...

Ngày tải lên: 08/03/2014, 18:20

... in the semantic space data and depending on the aspect, i.e. the initial- ly primed meaning point the algorithm is started with. Working its way through and consuming all lapeled points in ... to and a promising candidate for the simulation of contents- driven (analogically-associative), instead of for- mal (logically-deductive) inferences in semantic processing. I. The...

Ngày tải lên: 17/03/2014, 19:21

... es- timation for machine translation. In Proceedings of COLING. Michael Collins, Philipp Koehn, and Ivona Kucerova. 2005. Clause restructuring for statistical machine translation. In Proceedings of ... automatically generated train- ing labels for the supervised Machine Learning approach. In the experiments presented in this pa- per, we use BLEU scores (Papineni et al., 2002) as...

Ngày tải lên: 23/03/2014, 16:20

... proposes a domain-independent machine-learning based approach to assign activity times to events in news without deferring to the pub- lication date. Posing the problem in an informa- tion retrieval ... related work in temporal information processing. Next we moti- vate the use of topic models for our task, and present our methods for distributing temporal information. We conclude...

Ngày tải lên: 31/03/2014, 00:20

... backward-chnining inference, or top-down parnin~ We examine beurls- tics and strategies for problem localization in the context of using a planner to check for pragmatic failures in natural ... vertical bars. Initial question marks precede plea variables.) If a singie node In thls planning tree fails, say (IS-TEXT-FILE ?file), that Information can be used In explnining...

Ngày tải lên: 31/03/2014, 17:20

... person-machine advice-giving dialogues are realized by incorporating planning at a high-level of dialogue. Introduction As performances and scope of intelligent systems in- crease and the interaction ... when resolving references. Other domain knowledge for the problem formulation di- alogue is encoded in terms of the problem model objects and includes preferred sequences f...

Ngày tải lên: 09/03/2014, 01:20

... therefore essential to extract as much information as possible from each con- text of interest, allowing in this case for a long interaction period between each interviewed cattle veterinarian ... treatment of each individual cow, indicating that decisions can differ both within and between herds. At the farm level, the veterinarians seemed to integrate farm-related information into the d...

Ngày tải lên: 25/10/2012, 10:45

... Hideki Isozaki. 2007. Online large-margin training for statis- tical machine translation. In Proceedings of the 2007 20 Joint Conference on Empirical Mehtods in Natural Language Processing and Computational ... approach to scaling discrimina- tive learning for SMT not only to large feature sets but also to large sets of parallel training data. Since inference for SMT (unlike many ot...

Ngày tải lên: 19/02/2014, 19:20

... Linguistics Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System Wei-Bin Liang 1 Chung-Hsien Wu 2 Department of Computer Science and Information Engineering National ... overall intention via DA detection is an important task in SDS. Figure 1 depicts the training and test phases of the SLU module and the DM module in our system. The d...

Ngày tải lên: 20/02/2014, 05:20

... Issues in the Planning of Definite and Indefinite Noun Phrases Douglas E. Appelt Artificial Intelligence Center, SRI International and Center for the Study of Language and Information Stanford ... Stanford University 1 Introduction In this paper we examine the pragmatic knowledge an utterance-planning system must have in order to produce certain kinds of definite and indefin...

Ngày tải lên: 21/02/2014, 20:20