How Cute is Pikachu? Gathering and Ranking Pok\'emon Properties from Data with Pok\'emon Word Embeddings
Abstract
We present different methods for obtaining descriptive properties automatically for the 151 original Pok\'emon. We train several different word embeddings models on a crawled Pok\'emon corpus, and use them to rank automatically English adjectives based on how characteristic they are to a given Pok\'emon. Based on our experiments, it is better to train a model with domain specific data than to use a pretrained model. Word2Vec produces less noise in the results than fastText model. Furthermore, we expand the list of properties for each Pok\'emon automatically. However, none of the methods is spot on and there is a considerable amount of noise in the different semantic models. Our models have been released on Zenodo.
Cite
@article{arxiv.2108.09546,
title = {How Cute is Pikachu? Gathering and Ranking Pok\'emon Properties from Data with Pok\'emon Word Embeddings},
author = {Mika Hämäläinen and Khalid Alnajjar and Niko Partanen},
journal= {arXiv preprint arXiv:2108.09546},
year = {2021}
}
Comments
English translation of H\"am\"al\"ainen, M., Alnajjar, K. \& Partanen, N. (2021). Nettikorpuksen avulla tuotettuja sanavektorimalleja Pok\'emonien ominaisuuksien kuvaamiseksi. In Saarikivi, T. \& Saarikivi, J. (eds.) \textit{Turhan tiedon kirja -- Tutkimuksista pois j\"atettyj\"a sivuja}