Predicting Word Association Strengths

Andrew Cattle, Xiaojuan Ma


Abstract
This paper looks at the task of predicting word association strengths across three datasets; WordNet Evocation (Boyd-Graber et al., 2006), University of Southern Florida Free Association norms (Nelson et al., 2004), and Edinburgh Associative Thesaurus (Kiss et al., 1973). We achieve results of r=0.357 and p=0.379, r=0.344 and p=0.300, and r=0.292 and p=0.363, respectively. We find Word2Vec (Mikolov et al., 2013) and GloVe (Pennington et al., 2014) cosine similarities, as well as vector offsets, to be the highest performing features. Furthermore, we examine the usefulness of Gaussian embeddings (Vilnis and McCallum, 2014) for predicting word association strength, the first work to do so.
Anthology ID:
D17-1132
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1283–1288
Language:
URL:
https://aclanthology.org/D17-1132
DOI:
10.18653/v1/D17-1132
Bibkey:
Cite (ACL):
Andrew Cattle and Xiaojuan Ma. 2017. Predicting Word Association Strengths. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1283–1288, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Predicting Word Association Strengths (Cattle & Ma, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1132.pdf