Skip to main content

MetricBERT: Text Representation Learning via Self-Supervised Triplet Training

Itzik Malkiel, Dvir Ginzburg, Oren Barkan, Avi Caciularu, Yoni Weill, Noam Koenigstein

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:15:01
12 May 2022

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.