Martin Eineborg

Learn More
This paper reports a pilot study, in which Constraint Grammar inspired rules were learnt using the Progol machine-learning system. Rules discarding faulty readings of ambiguously tagged words were learnt for the part of speech tags of the Stockholm-Ume£ Corpus. Several thousand disambiguation rules were induced. When tested on unseen data, 98% of the words(More)
This paper reports the ongoing work of producing a state of the art part of speech tagger for unedited Swedish text. Rules eliminating faulty tags have been induced using Progol. In previously reported experiments, almost no linguistically motivated background knowledge was used 5, 8]. Still, the result was rather promising (recall 97.7%, with a pending(More)
The paper outlines a method for automatic lexical acquisition using three-layered back-propagation networks. Several experiments have been carried out where the performance of diierent network architectures have been compared to each other on two tasks: overall part-of-speech (noun, adjective or verb) classiication and classiication by a set of 13 possible(More)
A pilot study on inducing rules for part of speech tagging of unrestricted Swedish text is reported. Using the Progol machine-learning system, Constraint Grammar inspired rules were learnt from the part of speech tagged Stockholm-Ume a Corpus. Several thousand disambiguation rules discarding faulty readings of ambiguously tagged words were induced. When(More)
  • 1