@inproceedings{malkiel2022metricbert,
author = {Malkiel, Itzik and Ginzburg, Dvir and Barkan, Oren and Caciularu, Avi and Weill, Yoni and Koenigstein, Noam},
title = {MetricBERT: Text Representation Learning via Self-Supervised Triplet Training},
booktitle = {ICASSP 2022},
year = {2022},
month = {April},
abstract = {We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the “traditional” masked-language task. We focus on downstream tasks of learning similarities for recommendations where we show that MetricBERT outperforms state-of-the-art alternatives, sometimes by a substantial margin. We conduct extensive evaluations of our method and its different variants, showing that our training objective is highly beneficial over a traditional contrastive loss, a standard cosine similarity objective, and six other baselines. As an additional contribution, we publish a dataset of video games descriptions along with a test set of similarity annotations crafted by a domain expert.},
url = {http://approjects.co.za/?big=en-us/research/publication/metricbert-text-representation-learning-via-self-supervised-triplet-training/},
}