Yandex Uses DSSM Models (Algo Leak Jan 2023)

In the leaked Yandex ranking factors in January 2023, it has been confirmed that Yandex uses DSSM Models (Deep Semantic Similarity Mode) as part of its algorithm.

In fact, DSSM is used in 135 of the 1,922 named ranking factors.

What Is DSSM?

Semantic similarity is a metric defined over a set of documents or terms, where the idea of the distance between them is based on the likeness of their meaning or semantic content as opposed to similarity which can be estimated regarding their syntactical representation (e.g. their string format).

In context, DSSM is used to aid Alice Queries, as well as mentioned alongside the use of text relevance, relevance of words within sentences, alongside BERT, and for predicting the page quality score of a document.