GATE-Reranker-V1 ๐Ÿš€โœจ

NAMAA-space releases GATE-Reranker-V1, a high-performance model fine-tuned to elevate Arabic document retrieval and ranking to new heights! ๐Ÿ“š๐Ÿ‡ธ๐Ÿ‡ฆ

This model is designed to improve search relevance of arabic documents by accurately ranking documents based on their contextual fit for a given query.

Key Features ๐Ÿ”‘

  • Optimized for Arabic: Built on the highly performant Omartificial-Intelligence-Space/GATE-AraBert-v1 with exclusivly rich Arabic data.
  • Advanced Document Ranking: Ranks results with precision, perfect for search engines, recommendation systems, and question-answering applications.
  • State-of-the-Art Performance: Achieves excellent performance compared to famous rerankers(See Evaluation), ensuring reliable relevance and precision.

Example Use Cases ๐Ÿ’ผ

  • Retrieval Augmented Generation: Improve search result relevance for Arabic content.
  • Content Recommendation: Deliver top-tier Arabic content suggestions.
  • Question Answering: Boost answer retrieval quality in Arabic-focused systems.

Usage

Within sentence-transformers

The usage becomes easier when you have SentenceTransformers installed. Then, you can use the pre-trained models like this:

from sentence_transformers import CrossEncoder
model = CrossEncoder('NAMAA-Space/GATE-Reranker-V1', max_length=512)

Query = 'ูƒูŠู ูŠู…ูƒู† ุงุณุชุฎุฏุงู… ุงู„ุชุนู„ู… ุงู„ุนู…ูŠู‚ ููŠ ู…ุนุงู„ุฌุฉ ุงู„ุตูˆุฑ ุงู„ุทุจูŠุฉุŸ'
Paragraph1 = 'ุงู„ุชุนู„ู… ุงู„ุนู…ูŠู‚ ูŠุณุงุนุฏ ููŠ ุชุญู„ูŠู„ ุงู„ุตูˆุฑ ุงู„ุทุจูŠุฉ ูˆุชุดุฎูŠุต ุงู„ุฃู…ุฑุงุถ'
Paragraph2 = 'ุงู„ุฐูƒุงุก ุงู„ุงุตุทู†ุงุนูŠ ูŠุณุชุฎุฏู… ููŠ ุชุญุณูŠู† ุงู„ุฅู†ุชุงุฌูŠุฉ ููŠ ุงู„ุตู†ุงุนุงุช'

scores = model.predict([(Query, Paragraph1), (Query, Paragraph2)])

Evaluation

We evaluate our model on two different datasets using the metrics MAP, MRR and NDCG@10:

The purpose of this evaluation is to highlight the performance of our model with regards to: Relevant/Irrelevant labels and positive/multiple negatives documents:

Dataset 1: NAMAA-Space/Ar-Reranking-Eval

Plot

Dataset 2: NAMAA-Space/Arabic-Reranking-Triplet-5-Eval

Plot

As seen, The model performs extremly well in comparison to other famous rerankers.

WIP: More comparisons and evaluation on arabic datasets.

Downloads last month
131
Safetensors
Model size
135M params
Tensor type
F32
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for NAMAA-Space/GATE-Reranker-V1

Space using NAMAA-Space/GATE-Reranker-V1 1

Collection including NAMAA-Space/GATE-Reranker-V1