In this paper, we propose a novel framework for extractive summarization. Our framework allows the summarizer to adapt and improve itself. Experimental results show that our summa...
In this paper, we propose a new learning method for extracting bilingual word pairs from parallel corpora in various languages. In cross-language information retrieval, the system...
The paper analyzes peculiarities of preprocessing of learning data represented in object data bases constituted by multiple relational tables with ontology on top of it. Exactly s...
Abstract. We investigate the application of classification techniques to the problem of information extraction (IE). In particular we use support vector machines and several differ...
Abstract. In order to organize huge document collections, labeled hierarchical structures are used frequently. Users are most efficient in navigating such hierarchies, if they refl...