Neural Vector Conceptualization for Word Vector Space Interpretation

Robert Schwarzenberg, Lisa Raithel, David Harbecke


Abstract
Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models. In this work, we introduce a new method to interpret arbitrary samples from a word vector space. To this end, we train a neural model to conceptualize word vectors, which means that it activates higher order concepts it recognizes in a given vector. Contrary to prior approaches, our model operates in the original vector space and is capable of learning non-linear relations between word vectors and concepts. Furthermore, we show that it produces considerably less entropic concept activation profiles than the popular cosine similarity.
Anthology ID:
W19-2001
Volume:
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP
Month:
June
Year:
2019
Address:
Minneapolis, USA
Venues:
NAACL | RepEval | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–7
Language:
URL:
https://aclanthology.org/W19-2001
DOI:
10.18653/v1/W19-2001
Bibkey:
Cite (ACL):
Robert Schwarzenberg, Lisa Raithel, and David Harbecke. 2019. Neural Vector Conceptualization for Word Vector Space Interpretation. In Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP, pages 1–7, Minneapolis, USA. Association for Computational Linguistics.
Cite (Informal):
Neural Vector Conceptualization for Word Vector Space Interpretation (Schwarzenberg et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-2001.pdf
Code
 dfki-nlp/nvc