GTE - Base Open - Source Text Embedding Model: Efficiently Handle Sentence Similarity and Text Retrieval Tasks

Gte Base

Developed by thenlper

GTE-Base is a general-purpose text embedding model focused on sentence similarity and text retrieval tasks, performing well on multiple benchmarks.

Text Embedding EnglishOpen Source License:MIT #Multi-task Text Embedding #High-precision Semantic Similarity #Cross-domain Text Classification

Downloads 317.05k

Release Time : 7/27/2023

Model Overview

GTE-Base is a transformer-based sentence embedding model primarily used for generating high-quality sentence embeddings, suitable for tasks such as text similarity calculation, information retrieval, and text classification.

Model Features

Excellent Multi-task Performance

Performs consistently and excellently on various tasks including sentence similarity, text classification, clustering, and retrieval.

High-quality Sentence Embeddings

Capable of generating high-quality sentence-level embeddings suitable for various downstream NLP tasks.

Extensive Benchmark Validation

Comprehensively evaluated on multiple standard benchmark datasets such as MTEB.

Model Capabilities

Sentence similarity calculation

Text classification

Text clustering

Information retrieval

Semantic search

Text re-ranking

Use Cases

E-commerce

Product Review Classification

Sentiment polarity classification for Amazon product reviews

Achieved 91.77% accuracy on the AmazonPolarity dataset

Counterfactual Review Detection

Identifying counterfactual reviews on Amazon

Achieved 74.18% accuracy on the AmazonCounterfactual dataset

Customer Service

Banking Intent Classification

Intent classification for bank customer inquiries

Achieved 85.07% accuracy on the Banking77 dataset

Academic Research

Paper Clustering

Topic clustering for arXiv and biorxiv papers

Achieved 48.60% v_measure on the ArxivClusteringP2P dataset

🚀 gte-base

The gte-base model is a powerful tool in the field of natural language processing, with performance metrics across multiple tasks and datasets, including classification, retrieval, clustering, reranking, and semantic text similarity (STS).

📚 Documentation

Model Information

Property	Details
Model Name	gte-base
Tags	mteb, sentence-similarity, sentence-transformers, Sentence Transformers

Performance Metrics

Classification Tasks

Dataset	Accuracy	AP	F1
MTEB AmazonCounterfactualClassification (en)	74.17910447761193	36.827146398068926	68.11292888046363
MTEB AmazonPolarityClassification	91.77345000000001	88.33530426691347	91.76549906404642
MTEB AmazonReviewsClassification (en)	48.964	-	48.22995586184998
MTEB Banking77Classification	85.06818181818183	-	85.02524460098233

Retrieval Tasks

Dataset	MAP@1	MAP@10	MAP@100	MAP@1000	MRR@1	MRR@10	MRR@100	MRR@1000	NDCG@1	NDCG@10	NDCG@100	NDCG@1000	Precision@1	Precision@10	Precision@100	Precision@1000	Recall@1	Recall@10	Recall@100	Recall@1000
MTEB ArguAna	32.147999999999996	48.253	49.038	49.042	32.717	48.467	49.252	49.254999999999995	32.147999999999996	57.12199999999999	60.316	60.402	32.147999999999996	8.542	0.9900000000000001	0.1	32.147999999999996	85.42	99.004	99.644
MTEB CQADupstackAndroidRetrieval	32.411	45.162	46.717	46.836	39.914	51.534	52.185	52.22	39.914	52.235	57.4	58.982	39.914	10.258000000000001	1.6219999999999999	0.20500000000000002	32.411	65.408	87.248	96.951
MTEB CQADupstackEnglishRetrieval	31.911	42.608000000000004	43.948	44.089	40.064	48.916	49.539	49.583	40.064	48.442	52.798	54.871	40.064	9.178	1.452	0.193	31.911	58.155	76.46300000000001	89.622
MTEB CQADupstackGamingRetrieval	40.597	54.290000000000006	55.340999999999994	55.388999999999996	46.646	57.524	58.225	58.245999999999995	46.646	60.324999999999996	64.30900000000001	65.19	46.646	9.774	1.265	0.13799999999999998	40.597	74.773	91.61200000000001	97.726
MTEB CQADupstackGisRetrieval	27.122	36.711	37.775	37.842999999999996	29.153000000000002	38.873999999999995	39.739000000000004	39.794000000000004	29.153000000000002	42.048	47.144999999999996	48.901	29.153000000000002	6.4750000000000005	0.951	0.11299999999999999	27.122	56.279999999999994	79.597	92.804
MTEB CQADupstackMathematicaRetrieval	17.757	26.739	28.015	28.127999999999997	22.015	31.325999999999997	32.368	32.426	22.015	32.225	38.405	40.932	22.015	5.9830000000000005	1.051	0.13899999999999998	17.757	-	-	-

Clustering Tasks

Dataset	V-Measure
MTEB ArxivClusteringP2P	48.59706013699614
MTEB ArxivClusteringS2S	43.01463593002057
MTEB BiorxivClusteringP2P	38.20471092679967
MTEB BiorxivClusteringS2S	36.58967592147641

Reranking Task

Dataset	MAP	MRR
MTEB AskUbuntuDupQuestions	61.80250355752458	74.79455216989844

STS Task

Dataset	Cosine Similarity Pearson	Cosine Similarity Spearman	Euclidean Pearson	Euclidean Spearman	Manhattan Pearson	Manhattan Spearman
MTEB BIOSSES	89.87448576082345	87.64235843637468	88.4901825511062	87.74537283182033	88.39040638362911	87.62669542888003

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご