BLENDING FASTTEXT AND BERT PREDICTIONS FOR TAXONOMY ENRICHMENT

Dmitry Puzyrev, Ekaterina Artemova, Artem Shelmanov, Alexander PanchenkoKompʹûternaâ 2020 · DOI

Abstract

In this paper, we present one of the solutions to the Taxonomy Enrichment shared task co-located with the Dialogue conference. The proposed method blends distributional information from fastText and BERT word embeddings to predict the most likely parent hypernym node for a new term in a taxonomy. More specifically, we are using both the information on hypernym frequency among the most similar entries in the taxonomy and the similarity of hypernyms themselves. DeepPavlov-based fastText and RuBERT finetuned on news texts and Russian Wikipedia achieve a MAP of 0.3939 and MRR of 0.4353.
BibTeX
@inproceedings{puzyrev2020blending,
  author = {Dmitry Puzyrev and Ekaterina Artemova and Artem Shelmanov and Alexander Panchenko},
  title = {{BLENDING FASTTEXT AND BERT PREDICTIONS FOR TAXONOMY ENRICHMENT}},
  booktitle = {Kompʹûternaâ},
  year = {2020},
  doi = {10.28995/2075-7182-2020-19-1117-1122},
}

Loading related content...

Figure