Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.04506 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909428111900672 |
|---|---|
| author | Yu, Puxuan Merrick, Luke Nuti, Gaurav Campos, Daniel |
| author_facet | Yu, Puxuan Merrick, Luke Nuti, Gaurav Campos, Daniel |
| contents | This paper presents the training methodology of Arctic-Embed 2.0, a set of open-source text embedding models built for accurate and efficient multilingual retrieval. While prior works have suffered from degraded English retrieval quality, Arctic-Embed 2.0 delivers competitive retrieval quality on multilingual and English-only benchmarks, and supports Matryoshka Representation Learning (MRL) for efficient embedding storage with significantly lower compressed quality degradation compared to alternatives. We detail the design and implementation, presenting several important open research questions that arose during model development. We conduct experiments exploring these research questions and include extensive discussion aimed at fostering further discussion in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04506 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Arctic-Embed 2.0: Multilingual Retrieval Without Compromise Yu, Puxuan Merrick, Luke Nuti, Gaurav Campos, Daniel Computation and Language Information Retrieval Machine Learning This paper presents the training methodology of Arctic-Embed 2.0, a set of open-source text embedding models built for accurate and efficient multilingual retrieval. While prior works have suffered from degraded English retrieval quality, Arctic-Embed 2.0 delivers competitive retrieval quality on multilingual and English-only benchmarks, and supports Matryoshka Representation Learning (MRL) for efficient embedding storage with significantly lower compressed quality degradation compared to alternatives. We detail the design and implementation, presenting several important open research questions that arose during model development. We conduct experiments exploring these research questions and include extensive discussion aimed at fostering further discussion in this field. |
| title | Arctic-Embed 2.0: Multilingual Retrieval Without Compromise |
| topic | Computation and Language Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2412.04506 |