one of the complex documents in the real world is city maps. in these kinds of maps, text labels overlap by graphics with having a variety of fonts and styles in different orientations. usually, text and graphic colour is not predefined due to various map publishers. in most city maps, text and graphic lines form a single connected component. moreover, the common regions of text and graphic lin...

Topic segmentation was addressed by a large amount of work from which it is not easy to draw conclusions, especially about the need for knowledge. In this article, we propose in the same framework two methods for improving the results of a topic segmenter based on lexical reiteration. The first one is endogenous and exploits the distributional similarity of the words of a document for discoveri...

Topic segmentation was addressed by a large amount of work from which it is not easy to draw conclusions, especially about the need for knowledge. In this article, we propose to combine in the same framework two methods for improving the results of a topic segmenter based on lexical reiteration. The first one is endogenous and exploits the distributional similarity of words in a document for di...

In this paper we present Document analysis and classification system to segment and classify contents of Arabic document images. This system includes preprocessing, document segmentation, feature extraction and document classification. A document image is enhanced in the preprocessing by removing noise, binarization, and detecting and correcting image skew. In document segmentation, an algorith...

A quantitative representation of discourse structure can be computed by measuring lexical cohesion relations among adjacent text elements. These representations have previously been proposed to deal with sub-topic text segmentation. In a parallel corpus, similar representations can be derived for versions of a text in various languages. These can be used for parallel segmentation and as an alte...

In this paper, we describe novel methods for topic segmentation based on patterns of discourse organization. Using a corpus of news texts, our results show that it is possible to use discourse features (based on Rhetorical Structure Theory) for topic segmentation and that we outperform some well-known methods.

In this paper, we describe in brief our system for the Second International Chinese Word Segmentation Bakeoff sponsored by the ACL-SIGHAN. We participated in all tracks at the bakeoff. The evaluation results show our system can achieve an F measure of 0.9400.967 for different testing corpora.