Graph-Based Induction of Word Senses in Croatian

Marko Bekavac, Jan Šnajder


Abstract
Word sense induction (WSI) seeks to induce senses of words from unannotated corpora. In this paper, we address the WSI task for the Croatian language. We adopt the word clustering approach based on co-occurrence graphs, in which senses are taken to correspond to strongly inter-connected components of co-occurring words. We experiment with a number of graph construction techniques and clustering algorithms, and evaluate the sense inventories both as a clustering problem and extrinsically on a word sense disambiguation (WSD) task. In the cluster-based evaluation, Chinese Whispers algorithm outperformed Markov Clustering, yielding a normalized mutual information score of 64.3. In contrast, in WSD evaluation Markov Clustering performed better, yielding an accuracy of about 75%. We are making available two induced sense inventories of 10,000 most frequent Croatian words: one coarse-grained and one fine-grained inventory, both obtained using the Markov Clustering algorithm.
Anthology ID:
L16-1481
Volume:
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Month:
May
Year:
2016
Address:
Portorož, Slovenia
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
3014–3018
Language:
URL:
https://aclanthology.org/L16-1481
DOI:
Bibkey:
Cite (ACL):
Marko Bekavac and Jan Šnajder. 2016. Graph-Based Induction of Word Senses in Croatian. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3014–3018, Portorož, Slovenia. European Language Resources Association (ELRA).
Cite (Informal):
Graph-Based Induction of Word Senses in Croatian (Bekavac & Šnajder, LREC 2016)
Copy Citation:
PDF:
https://aclanthology.org/L16-1481.pdf