60 citations · 79 across the 10 of their papers we have counts for
3 papers · 1 filter
Interpreting BERT-based Text Similarity via Activation and Saliency Maps
Itzik Malkiel, Dvir Ginzburg, Oren Barkan +3
Recently, there has been growing interest in the ability of Transformer-based models to produce meaningful embeddings of text with several applications, such as text similarity. De…
MetricBERT: Text Representation Learning via Self-Supervised Triplet Training
Itzik Malkiel, Dvir Ginzburg, Oren Barkan +3
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…
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference
Dvir Ginzburg, Itzik Malkiel, Oren Barkan +2
We present a novel model for the problem of ranking a collection of documents according to their semantic similarity to a source (query) document. While the problem of document-to-…