A Rank-based Distance Measure to Detect Polysemy and to Determine Salient Vector-Space Features for German Prepositions

Maximilian Köper, Sabine Schulte im Walde


Abstract
This paper addresses vector space models of prepositions, a notoriously ambiguous word class. We propose a rank-based distance measure to explore the vector-spatial properties of the ambiguous objects, focusing on two research tasks: (i) to distinguish polysemous from monosemous prepositions in vector space; and (ii) to determine salient vector-space features for a classification of preposition senses. The rank-based measure predicts the polysemy vs. monosemy of prepositions with a precision of up to 88%, and suggests preposition-subcategorised nouns as more salient preposition features than preposition-subcategorising verbs.
Anthology ID:
L14-1483
Volume:
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
Month:
May
Year:
2014
Address:
Reykjavik, Iceland
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
4459–4466
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/599_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Maximilian Köper and Sabine Schulte im Walde. 2014. A Rank-based Distance Measure to Detect Polysemy and to Determine Salient Vector-Space Features for German Prepositions. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4459–4466, Reykjavik, Iceland. European Language Resources Association (ELRA).
Cite (Informal):
A Rank-based Distance Measure to Detect Polysemy and to Determine Salient Vector-Space Features for German Prepositions (Köper & Schulte im Walde, LREC 2014)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/599_Paper.pdf