Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models

Michael Günther, Georgios Mastrapas, Bo Wang, Han Xiao, Jonathan Geuter

Keywords: embedding models, large language models

TL;DR: This paper presents Jina Embeddings, high-performance sentence embedding models, detailing their development process and demonstrating their effectiveness on the Massive Textual Embedding Benchmark (MTEB).

Abstract:

Jina Embeddings constitutes a set of high-performance sentence embedding models adept at translating textual inputs into numerical representations, capturing the semantics of the text. These models excel in applications like dense retrieval and semantic textual similarity. This paper details the development of Jina Embeddings, starting with the creation of high-quality pairwise and triplet datasets.
It underlines the crucial role of data cleaning in dataset preparation, offers in-depth insights into the model training process, and concludes with a comprehensive performance evaluation using the Massive Text Embedding Benchmark (MTEB). Furthermore, to increase the model's awareness of grammatical negation, we construct a novel training and evaluation dataset of negated and non-negated statements, which we make publicly available to the community.

Submission Number: 5