Deriving Boolean structures from distributional vectors

German Kruszewski, Denis Paperno, Marco Baroni


Abstract
Corpus-based distributional semantic models capture degrees of semantic relatedness among the words of very large vocabularies, but have problems with logical phenomena such as entailment, that are instead elegantly handled by model-theoretic approaches, which, in turn, do not scale up. We combine the advantages of the two views by inducing a mapping from distributional vectors of words (or sentences) into a Boolean structure of the kind in which natural language terms are assumed to denote. We evaluate this Boolean Distributional Semantic Model (BDSM) on recognizing entailment between words and sentences. The method achieves results comparable to a state-of-the-art SVM, degrades more gracefully when less training data are available and displays interesting qualitative properties.
Anthology ID:
Q15-1027
Volume:
Transactions of the Association for Computational Linguistics, Volume 3
Month:
Year:
2015
Address:
Cambridge, MA
Editors:
Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
375–388
Language:
URL:
https://aclanthology.org/Q15-1027
DOI:
10.1162/tacl_a_00145
Bibkey:
Cite (ACL):
German Kruszewski, Denis Paperno, and Marco Baroni. 2015. Deriving Boolean structures from distributional vectors. Transactions of the Association for Computational Linguistics, 3:375–388.
Cite (Informal):
Deriving Boolean structures from distributional vectors (Kruszewski et al., TACL 2015)
Copy Citation:
PDF:
https://aclanthology.org/Q15-1027.pdf
Video:
 https://aclanthology.org/Q15-1027.mp4
Data
SICK