EUROSPEECH 2003 - INTERSPEECH 2003
The extraction of lexical information for machine readable lexica from multilevel annotations is addressed in this paper. Relations between these levels of annotation are used for sub-classification of lexical entries. A method for relating annotation units is presented, based on a temporal calculus. Relating the annotation units manually is error-prone, time consuming and tends to be inconsistent, and a method is presented for automatically accomplishing this task, and evaluated using German, Japanese and Anyi (W. Africa) corpora.
Bibliographic reference. Trippel, Thorsten / Sasaki, Felix / Hell, Benjamin / Gibbon, Dafydd (2003): "Acquiring lexical information from multilevel temporal annotations", In EUROSPEECH-2003, 2265-2268.