Semantic segmentation aims at jointly computing a segmentation and a semantic labeling of the image plane. The main ingredient is an efficient feature selection strategy. In this work we perform a systematic information-theoretic evaluation of existing features in order to address the question which and how many features are appropriate for an efficient semantic segmentation. To this end, we di...

This paper shows that semantic role labeling is a consequence of accurate verbal predicate labeling. In doing so, the paper presents a novel type of semantic feature for verbal predicate labeling using a new corpus. The corpus contains verbal predicates, serving as verb senses, that have semantic roles associated with each argument. Although much work has been done using feature vectors with ma...

Semantic annotation influence on coreference detection using perceptron approach The ConLL-2011/2012 evaluation campaign was dedicated to coreference detection systems. This paper presents the coreference resolution system Poly-co submitted to the closed track of the CoNLL-2011 Shared Task and evaluate is potential of evolution when it includes a semantic feature. Our system integrates a multil...

An important precondition for the success of the Semantic Web is founded on the principle that the content of web pages will be semantically annotated. In this paper, we propose a method, CMSA, of automatically acquiring semantic annotations. In the CMSA method, semantic annotations are acquired from semantic relationships. Class hierarchy is used to describe semantic relationships. One key fea...

To study the generation of the semantic tree of Chinese sentence in Chinese-English Machine translation (MT), a new semantic-analysis model of Chinese multiplebranched and multiple-labeled tree (MMT) based on the hierarchical network of concepts (HNC) is proposed. Supported by word and rule knowledge-base of HNC, the model executed the semantic analysis using static and dynamic labels as a comp...

We present ExB Themis – a word alignmentbased semantic textual similarity system developed for SemEval-2015 Task 2: Semantic Textual Similarity. It combines both string and semantic similarity measures as well as alignment features using Support Vector Regression. It occupies the first three places on Spanish data and additionally places second on English data. ExB Themis proved to be the best ...

In process planning, how to obtain an optimal process planning is the essential of computer-aided process planning (CAPP) system. The main goal of CAPP system is to derive manufacturing features and machining operations from a design model and sequence the machining operations of the part in a feasible (by some technological constraints) and effective (by some economical standards) order. In th...

Although the fast development of OGC (Open Geospatial Consortium) WFS (Web Feature Service) technologies has undoubtedly improved the sharing and synchronization of feature-level geospatial information across diverse resources, literature shows that there are still apparent limitations in the current implementation of OGC WFSs. Currently, the implementation of OGC WFSs only emphasizes syntactic...