Báo cáo khoa học: "Trainable Sentence Planning for Complex Information Presentation in Spoken Dialog Systems" pot

... information gathering phase of the dialog, and with simple content plans in- volving no rhetorical relations. This paper describes trainable sentence planning for information presentation in ... domains. For example, the training method used in SPoT (Sentence Planner Train- able), as described in (Walker, Rambow and Ro- gati, 2002), was only shown to work in the trav...

Ngày tải lên: 23/03/2014, 19:20

... context information is taken into account, when searching for the meaning of such a word. In this paper, I will present the incremental ontology learning framework On2L. The defined tasks for the ... most suitable information beforehand. In the case of finding hypernyms the first sentence in the encyclopedia description is most useful. To give an example, here is the first senten...

Ngày tải lên: 23/03/2014, 18:20

... self- training for improving parse reranking. Other relevant recent work includes (Zhang, 2004), in which random feature projection and a committee of SVM classifiers is used in a hybrid co/self-training ... addressed in section 10.3. In this study we develop a learning model based around the concept of iteratively predicting labels for unlabelled training samples, the basic paradi...

Ngày tải lên: 23/03/2014, 18:20

... acquire a domain specific generation dictionary for information presentation in a dialogue system. Our hypothesis is that re- views that provide individual ratings for various distinguished attributes ... method for learning such mappings from user re- views in the target domain, and test it on restaurant reviews. We test the hypothesis that user reviews that provide individual r...

Ngày tải lên: 23/03/2014, 18:20

... Lab. of Intelligent Information Processing + Key Lab. of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704, Beijing 100190, China {xionghao,xuwenwen,htmi,yliu,liuqun}@ict.ac.cn ... other hand, decoding on long sentences will be time consuming, especially for forest ap- proaches. So splitting long sentences into sub- Figu...

Ngày tải lên: 31/03/2014, 00:20

... starring Mira Sorvino”. Handwriting: Handwritten pen input can also be used to make queries. When the user’s pen ap- proaches the feedback window, it expands allow- ing for freeform pen input. In ... alignment of multimodal inputs, multimodal integration, and language un- derstanding within a single mechanism. The result- ing combined meaning representation (represented in XML) is pa...

Ngày tải lên: 20/02/2014, 12:20

... to contain enough information for auto- matic summarization, but still be practicable for hand coding. Annotation proceeds sentence by sentence ac- cording to the decision tree given in Figure ... add considerable value to the information contained in the training material. Study III tries to answer the question whether the considerable training effort used in Studies...

Ngày tải lên: 22/02/2014, 03:20

... induced, followed by pulse labelling with [ 35 S]methionine. After 2 min, cold methionine was added to stop the labelling, and cells were collected and incubated for 10 min in buffer containing ... distinct target- ing and insertion pathways to reach their final destina- tion in the inner membrane [1]. However, the exact requirements for targeting and membrane insertion have been teste...

Ngày tải lên: 07/03/2014, 02:20

... challenges in the NXT-to-database conversion is the extraction of relevant information, which is done here by solving NXT pointers and discarding NXT-specific markup to group all information for a ... The stylesheets resolve most of the NXT pointers, by including redundant information into the tables, in order to speed up queries by avoiding frequent joins. A Perl script applies the...

Ngày tải lên: 08/03/2014, 02:21

... and generalization of vector models in information retrieval. In Proceedings of the 6th Annual International Conference on Research and Devel- opment in Information Retrieval, pages 118-132. ... probabilistic model. In Information Technology, volume 3, pages 113-114. Ido Dagan and Kenneth W. Church. 1994. Termight: Iden- tifying and translating technical terminology. I...

Ngày tải lên: 08/03/2014, 05:21