DFKI-LT - Neural Vector Conceptualization for Word Vector Space Interpretation
Neural Vector Conceptualization for Word Vector Space Interpretation
3 NAACL-HLT 2019 Workshop on Evaluating Vector Space Representations for NLP (RepEval), MInneapolis, Minnesota, USA, Association for Computational Linguistics, 2019
Distributed word vector spaces are considered hard to interpret which hinders the under-standing 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.
Files: BibTeX, neural_vector_conceptualization.pdf