Abstract | ||
---|---|---|
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 annota- tion 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 auto- matically accomplishing this task, and evaluated using German, Japanese and Anyi (W. Africa) corpora. 1. Objective The extraction of lexical information from multilevel annota- tions is the objective of this paper1. With existing annotations on multiple levels there are at least two ways of extracting in- formation using relations between two or more layers: |
Year | Venue | Field |
---|---|---|
2003 | INTERSPEECH | Computer science,Speech recognition,Natural language processing,Artificial intelligence |
DocType | Citations | PageRank |
Conference | 1 | 0.43 |
References | Authors | |
6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thorsten Trippel | 1 | 45 | 14.10 |
Felix Sasaki | 2 | 30 | 13.29 |
Benjamin Hell | 3 | 18 | 2.46 |
Dafydd Gibbon | 4 | 129 | 40.03 |