Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication - Volume 11, Issue 1, 2005

In this paper, we present an experiment dealing with corpus-based construction of “differential ontologies”, which are organised according to semantic similarity and differential features. We argue that knowledge-rich defining contexts can be useful to help an ontology modeller in his task. We present a method, based on lexico-syntactic patterns, to spot such contexts in a corpus, then identify the terms they relate (definiendum and genus or “characteristics”) and the semantic relation that links them. We also show how potential co-hyponyms can be detected on the basis of shared words in their definiens. We evaluate the extracted defining sentences, semantic relations and co-hyponyms on a test corpus focusing on childhood and on an evaluation corpus about dietetics (both corpora are French). Definition extraction obtains 50% precision and recall of approximately 40%. Semantic relation identification reaches an average of 48% precision, and co-hyponyms 23.5%. We discuss the results of these experiments and conclude on perspectives for future work.

This paper discusses a method for corpus-driven ontology design: extracting conceptual hierarchies from arbitrary domain-specific collections of texts. These hierarchies can form the basis for a concept-oriented (onomasiological) terminology collection, and hence may be used as the basis for developing knowledge-based systems using ontology editors. This reference to ontology is explored in the context of collections of terms. The method presented is a hybrid of statistical and linguistic techniques, employing statistical techniques initially to elicit a conceptual hierarchy, which is then augmented through linguistic analysis. The result of such an extraction may be useful in information retrieval, knowledge management, or in the discipline of terminology science itself.

This paper covers ongoing terminography work in the FF POIROT project, a European research project in which formal and shareable knowledge repositories (i.e. ontologies) and ontology-based applications are developed for the prevention of value added tax carousel fraud in the EU and the detection of securities fraud. We will emphasise that the knowledge requirements regarding users and applications determine what textual information should be structured at macro- and micro-levels of the FF POIROT multilingual terminology base. Furthermore, we will present our ideas concerning a multidisciplinary approach in terminography, called ‘Termontography’, for future application-oriented terminology development.

Collocation dictionaries are essential in specialized discourse for understanding, production, and translation. Especially translation, which is often undertaken by professionals who are not specialists of the field, is in need of dictionaries with detailed syntactic and semantic information on lexical and semantic links between terms. However, collocation dictionaries are hardly available for general, let alone specialized, discourse. The manual compilation of collocation dictionaries from large corpora is a time consuming and cost-intensive procedure. A (partial) automation of this procedure recently became a high-priority topic in computational lexicography. In this article, we discuss how collocations can be acquired from specialized corpora and labeled with semantic tags using machine-learning techniques. As semantic tags, we use lexical functions from the Explanatory Combinatorial Lexicology. We explore the performance of two different machine-learning techniques, Nearest Neighbor Classification and Tree Augmented Bayesian Classification, testing them on a Spanish law corpus.

Terminology variation in texts is now a well-known phenomenon, whose amount is estimated to be between 15% to 35%, depending on the domain, text type and kind of variants identified. In this paper, we present different typologies of variants elaborated for application-oriented terminology engineering and synthesise them in order to derive a core of variations. We shall show that the semantic interpretation of the variation depends on the application. Even if terminology variation remains a problem in various applications, it also provides clues that could be exploited in these same applications. We illustrate what benefit they bring and conclude by highlighting future trends of variation studies.

This paper presents an original natural language processing (NLP) approach for building of back-of-the-book indexes. Our indexing system, IndDoc, exploits some terminological tools and automatically builds an index draft of the analysis of the document text. The indexer then has to validate that index draft through a dedicated interface. This approach has been tested on several documents with promising results. Relying on our experience in developing and testing the IndDoc indexing system, we aim at assessing the contribution of terminological analysis as well as the level of maturity that computational terminology has reached in the indexing perspective.