The most comprehensive implementation of a Semantic Execution Environment (SEE) is currently represented by WSMX, which can however support only single-instance deployments. In this paper we discuss the motivations behind distributed scenarios and outline the issues to be addressed in order for WSMX to support them.

Discourse incoherence is an important and typical problem with multi-document extractive summaries. To address this issue, we have developed a schema-based summarization approach for query-based blog summaries that utilizes discourse structures. In our schema design, we tried to model discourse structures which are typically used by humans in their summary writing in response to a particular qu...

In this paper we propose a trainable method for extracting Chinese entity names and their relations. We view the entire problem as series of classification problems and employ memory-based learning (MBL) to resolve them. Preliminary results show that this method is efficient, flexible and promising to achieve better performance than other existing methods.

We study the savings afforded by repeated use in two zero-error communication problems. We show that for some random sources, communicating one instance requires arbitrarily-many bits, but communicating multiple instances requires roughly one bit per instance. We also exhibit sources where the number of bits required for a single instance is comparable to the source’s size, but two instances re...

The multiplication of execution contexts for multimedia documents requires the adaptation of document specifications. This paper instantiates our previous semantic approach for multimedia document adaptation to the spatial dimension of multimedia documents. Our goal is to find a qualitative spatial representation that computes, in a reasonable time, a set of adaptation solutions close to the in...

Han Bao The University of Tokyo, 113-0033 Tokyo, Japan [email protected] Tomoya Sakai The University of Tokyo, 277-8561 Chiba, Japan RIKEN Center for AIP, 103-0027 Tokyo, Japan [email protected] Masashi Sugiyama RIKEN Center for AIP, 103-0027 Tokyo, Japan The University of Tokyo, 277-8561 Chiba, Japan [email protected] Issei Sato The University of Tokyo, 277-8561 Chiba, Japa...

While Machine Learning algorithms are key to automating organelle segmentation in large EM stacks, they require annotated data, which is hard to come by in sufficient quantities. Furthermore, images acquired from one part of the brain are not always representative of another due to the variability in the acquisition and staining processes. Therefore, a classifier trained on the first may perfor...

In this paper, we develop an efficient logistic regression model for multiple instance learning that combines L1 andL2 regularisation techniques. AnL1 regularised logistic regression model is first learned to find out the sparse pattern of the features. To train the L1 model efficiently, we employ a convex differentiable approximation of the L1 cost function which can be solved by a quasi Newto...

In current search engines, ranking functions are learned from a large number of labeled pairs in which the labels are assigned by human judges, describing how well the URLs match the different queries. However in commercial search engines, collecting high quality labels is time-consuming and labor-intensive. To tackle this issue, this paper studies how to produce the true relevance...

Record linkage is the process of identifying records that refer to the same entities from different data sources. While most research efforts are concerned with linking individual records, new approaches have recently been proposed to link groups of records across databases. Group record linkage aims to determine if two groups of records in two databases refer to the same entity or not. One app...