Data-driven identification of German phrasal compounds
- We present a method to identify and document a phenomenon on which there is very little empirical data: German phrasal compounds occurring in the form of as a single token (without punctuation between their components). Relying on linguistic criteria, our approach implies to have an operational notion of compounds which can be systematically applied as well as (web) corpora which are large and diverse enough to contain rarely seen phenomena. The method is based on word segmentation and morphological analysis, it takes advantage of a data-driven learning process. Our results show that coarse-grained identification of phrasal compounds is best performed with empirical data, whereas fine-grained detection could be improved with a combination of rule-based and frequency-based word lists. Along with the characteristics of web texts, the orthographic realizations seem to be linked to the degree of expressivity.
Download full text files
- Barbaresi_Hein_Data_driven_2017.pdf
(Printversion - IDS-intern)
- Barbaresi_Hein_Data_driven_2017_FINAL-DRAFT.pdf
(Postprint - IDS-intern)
Additional Services
Statistics
| Author: | Adrien Barbaresi, Katrin Hein |
|---|---|
| URN: | urn:nbn:de:bsz:mh39-63888 |
| URL: | https://hal.archives-ouvertes.fr/hal-01575651/document |
| DOI: | https://doi.org/10.1007/978-3-319-64206-2_22 |
| ISBN: | 978-3-319-64205-5 |
| Parent Title (English): | Text, Speech, and Dialogue. 20th International Conference, TSD 2017, Prague, Czech Republic, August 27-31, 2017, proceedings |
| Series (Serial Number): | Lecture Notes in Computer Science (10415) |
| Publisher: | Springer |
| Place of publication: | Cham |
| Editor: | Kamil Ekštein, Václav Matoušek |
| Document Type: | Part of a Book |
| Language: | English |
| Year of first Publication: | 2017 |
| Date of Publication (online): | 2017/08/30 |
| Publicationstate: | Postprint |
| Reviewstate: | Peer-Review |
| Tag: | corpus linguistics; morphological analysis; web corpora; word segmentation |
| GND Keyword: | Deutsch; Korpus <Linguistik>; Morphemanalyse; Segmentierung; Wort |
| First Page: | 192 |
| Last Page: | 200 |
| DDC classes: | 400 Sprache / 430 Deutsch |
| Open Access?: | nein |
| Program areas: | Lexik |
| Licence (German): |  Urheberrechtlich geschützt |