Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell

Pia Sommerauer, Antske Fokkens


Abstract
This paper presents an approach for investigating the nature of semantic information captured by word embeddings. We propose a method that extends an existing human-elicited semantic property dataset with gold negative examples using crowd judgments. Our experimental approach tests the ability of supervised classifiers to identify semantic features in word embedding vectors and compares this to a feature-identification method based on full vector cosine similarity. The idea behind this method is that properties identified by classifiers, but not through full vector comparison are captured by embeddings. Properties that cannot be identified by either method are not. Our results provide an initial indication that semantic properties relevant for the way entities interact (e.g. dangerous) are captured, while perceptual information (e.g. colors) is not represented. We conclude that, though preliminary, these results show that our method is suitable for identifying which properties are captured by embeddings.
Anthology ID:
W18-5430
Volume:
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Tal Linzen, Grzegorz Chrupała, Afra Alishahi
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
276–286
Language:
URL:
https://aclanthology.org/W18-5430
DOI:
10.18653/v1/W18-5430
Bibkey:
Cite (ACL):
Pia Sommerauer and Antske Fokkens. 2018. Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 276–286, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell (Sommerauer & Fokkens, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5430.pdf