Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913222754304000 |
|---|---|
| author | Günther, Michael Ong, Jackmin Mohr, Isabelle Abdessalem, Alaeddine Abel, Tanguy Akram, Mohammad Kalim Guzman, Susana Mastrapas, Georgios Sturua, Saba Wang, Bo Werk, Maximilian Wang, Nan Xiao, Han |
| author_facet | Günther, Michael Ong, Jackmin Mohr, Isabelle Abdessalem, Alaeddine Abel, Tanguy Akram, Mohammad Kalim Guzman, Susana Mastrapas, Georgios Sturua, Saba Wang, Bo Werk, Maximilian Wang, Nan Xiao, Han |
| contents | Text embedding models have emerged as powerful tools for transforming sentences into fixed-sized feature vectors that encapsulate semantic information. While these models are essential for tasks like information retrieval, semantic clustering, and text re-ranking, most existing open-source models, especially those built on architectures like BERT, struggle to represent lengthy documents and often resort to truncation. One common approach to mitigate this challenge involves splitting documents into smaller paragraphs for embedding. However, this strategy results in a much larger set of vectors, consequently leading to increased memory consumption and computationally intensive vector searches with elevated latency.
To address these challenges, we introduce Jina Embeddings 2, an open-source text embedding model capable of accommodating up to 8192 tokens. This model is designed to transcend the conventional 512-token limit and adeptly process long documents. Jina Embeddings 2 not only achieves state-of-the-art performance on a range of embedding-related tasks in the MTEB benchmark but also matches the performance of OpenAI's proprietary ada-002 model. Additionally, our experiments indicate that an extended context can enhance performance in tasks such as NarrativeQA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_19923 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents Günther, Michael Ong, Jackmin Mohr, Isabelle Abdessalem, Alaeddine Abel, Tanguy Akram, Mohammad Kalim Guzman, Susana Mastrapas, Georgios Sturua, Saba Wang, Bo Werk, Maximilian Wang, Nan Xiao, Han Computation and Language Artificial Intelligence Machine Learning 68T50 I.2.7 Text embedding models have emerged as powerful tools for transforming sentences into fixed-sized feature vectors that encapsulate semantic information. While these models are essential for tasks like information retrieval, semantic clustering, and text re-ranking, most existing open-source models, especially those built on architectures like BERT, struggle to represent lengthy documents and often resort to truncation. One common approach to mitigate this challenge involves splitting documents into smaller paragraphs for embedding. However, this strategy results in a much larger set of vectors, consequently leading to increased memory consumption and computationally intensive vector searches with elevated latency. To address these challenges, we introduce Jina Embeddings 2, an open-source text embedding model capable of accommodating up to 8192 tokens. This model is designed to transcend the conventional 512-token limit and adeptly process long documents. Jina Embeddings 2 not only achieves state-of-the-art performance on a range of embedding-related tasks in the MTEB benchmark but also matches the performance of OpenAI's proprietary ada-002 model. Additionally, our experiments indicate that an extended context can enhance performance in tasks such as NarrativeQA. |
| title | Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents |
| topic | Computation and Language Artificial Intelligence Machine Learning 68T50 I.2.7 |
| url | https://arxiv.org/abs/2310.19923 |