This paper deals with the problem of recognizing and extracting acronymdefinition pairs in Swedish medical texts. This project applies a rule-based method to solve the acronym recognition task and compares and evaluates the results of different machine learning algorithms on the same task. The method proposed is based on the approach that acronym-definition pairs follow a set of patterns and other regularities that can be usefully applied for the acronym identification task. Supervised machine learning was applied to monitor the performance of the rule-based method, using Memory Based Learning (MBL). The rule-based algorithm was evaluated on a hand tagged acronym corpus and performance was measured using standard measures recall, precision and fscore. The results show that performance could further improve by increasing the training set and modifying the input settings for the machine learning algorithms. An analysis of the errors produced indicates that further improvement of the rulebased method requires the use of syntactic information and textual pre-processing.

No abstract

No abstract

Having access to large lexical and grammatical resources when creating a new language resource is essential for its enhancement and enrichment. This paper describes the interplay and interactive utilization of different language technology tools and resources, in particular the Swedish lexicon SALDO and Swedish Constructicon, in the creation of Swedish FrameNet. We show how integrating resources in a larger infrastructure is much more than the sum of the parts.

No abstract