Exploiting Morphological Regularities in Distributional Word Representations

Arihant Gupta, Syed Sarfaraz Akhtar, Avijit Vajpayee, Arjit Srivastava, Madan Gopal Jhanwar, Manish Shrivastava


Abstract
We present an unsupervised, language agnostic approach for exploiting morphological regularities present in high dimensional vector spaces. We propose a novel method for generating embeddings of words from their morphological variants using morphological transformation operators. We evaluate this approach on MSR word analogy test set with an accuracy of 85% which is 12% higher than the previous best known system.
Anthology ID:
D17-1028
Original:
D17-1028v1
Version 2:
D17-1028v2
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
292–297
Language:
URL:
https://www.aclweb.org/anthology/D17-1028
DOI:
10.18653/v1/D17-1028
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1028.pdf