Irion Technologies is a language technology company at Delft (The Netherlands) that incorporates linguistic knowledge to build new generations of information systems: conceptual retrieval, automatic extraction of terms and ontologies and open-domain dialogue systems. These systems are multi-lingual and cross-lingual and combine statistical, machine learning techniques with linguistic techniques. We have carried out evaluations of some of these systems. For information retrieval, we found advantages with respect to standard statistical approaches within special experimental settings that focus on ambiguity. Term extraction is clearly benefiting from rich linguistic knowledge and resources. Dialogue systems depend on the communicative models and systems that also require deep linguistic processing. From our perspective, language technology is definitely helping to make applications better and necessary to develop new applications.

A summary is a condensed version of a document. It contains the most relevant information in context found in the source document. Automatic summarization is the process of producing text summaries by computer. Although research on automatic summarization started in the late 50s, the increasing volume of electronic text and recent international evaluation efforts have fuelled research in this field. The paper gives an overview of basic concepts in automatic text summarization together with examples of available tools, systems, evaluation, summarization experiments, summarization in practical settings, and discusses the role of linguistic information in the summarization task.

The automatic or semi-automatic processing of texts often requires an access to external resources (e.g., lexical and terminological databases or ontologies), which can differ greatly in terms of both form and content. External resources can be used to assist other forms of processing and are expected to supply linguistic information - especially semantic information - that is not explicitly expressed in running text. In this article, the potential interest of lexical and terminological sources as well as ontologies for analyzing terms in specialized texts will be examined and evaluated. The evaluation takes into account the contents and the descriptive perspective of sources. We will focus on the field of computing assuming that this domain is representative of many others. The presence and description of 75 specific terms has been analyzed in six different sources. Results show that sources do not take into account the entire set of linguistic properties of terms.