gte-large Open-Source Sentence Transformer Model - Free to Use for Precise Handling of Sentence Similarity and Text Embedding

Gte Large

Developed by thenlper

GTE-Large is a powerful sentence transformer model focused on sentence similarity and text embedding tasks, excelling in multiple benchmark tests.

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

Downloads 1.5M

Release Time : 7/27/2023

Model Overview

GTE-Large is a general-purpose text embedding model capable of converting sentences into high-dimensional vector representations for tasks such as similarity calculation, classification, clustering, and information retrieval.

Model Features

Excellent Multitask Performance

Balanced performance across various NLP tasks including classification, retrieval, and clustering.

High-quality Sentence Embeddings

Generated sentence embeddings effectively capture semantic information.

Extensive Benchmark Validation

Comprehensively evaluated on multiple benchmark datasets including MTEB.

Model Capabilities

Sentence similarity calculation

Text classification

Information retrieval

Text clustering

Sentence vectorization

Use Cases

E-commerce

Product Review Sentiment Analysis

Analyze sentiment tendencies of Amazon product reviews.

Achieved 92.5% accuracy on the AmazonPolarity dataset.

Counterfactual Review Detection

Identify counterfactual reviews on Amazon.

Achieved 72.6% accuracy on the AmazonCounterfactual dataset.

Academic Research

Paper Clustering

Topic clustering for arXiv and biorxiv papers.

Achieved V-measure of 48.6 on arXiv P2P clustering task.

Customer Service

Banking Issue Classification

Automatic classification of banking customer issues.

Achieved 86.1% accuracy on the Banking77 dataset.

🚀 gte-large

The gte-large model is designed for various natural language processing tasks, including classification, retrieval, clustering, reranking, and semantic text similarity (STS). It provides performance metrics across multiple datasets, offering insights into its effectiveness in different scenarios.

📚 Documentation

Model Information

Property	Details
Model Type	gte-large
Tags	mteb, sentence-similarity, sentence-transformers, Sentence Transformers

Performance Metrics

Classification Tasks

Dataset	Accuracy	AP	F1
MTEB AmazonCounterfactualClassification (en)	72.62686567164178	34.46944126809772	66.23684353950857
MTEB AmazonPolarityClassification	92.51805	89.49842783330848	92.51112169431808
MTEB AmazonReviewsClassification (en)	49.074	N/A	48.44785682572955
MTEB Banking77Classification	86.05844155844157	N/A	86.01555597681825

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	32.077	48.153	48.963	48.966	33.073	48.54	49.335	49.338	32.077	57.158	60.324999999999996	60.402	32.077	8.591999999999999	0.991	0.1	32.077	85.917	99.075	99.644
MTEB CQADupstackAndroidRetrieval	32.800000000000004	44.857	46.512	46.635	39.628	50.879	51.605000000000004	51.641000000000005	39.628	51.819	57.318999999999996	58.955999999999996	39.628	10.072000000000001	1.625	0.21	32.800000000000004	65.078	87.491	97.514
MTEB CQADupstackEnglishRetrieval	32.614	43.578	44.897	45.023	40.510000000000005	49.428	50.068999999999996	50.111000000000004	40.510000000000005	49.478	53.852	55.782	40.510000000000005	9.363000000000001	1.51	0.196	32.614	59.782000000000004	78.012	90.319
MTEB CQADupstackGamingRetrieval	40.266000000000005	53.756	54.809	54.855	46.332	57.116	57.767	57.791000000000004	46.332	60.092	64.034	64.937	46.332	9.799	1.278	0.13899999999999998	40.266000000000005	75.41499999999999	92.01700000000001	98.379
MTEB CQADupstackGisRetrieval	28.589	37.755	38.881	38.954	30.734	39.742	40.774	40.824	30.734	42.978	48.309000000000005	50.068	30.734	6.565	0.964	0.11499999999999999	28.589	57.126999999999995	81.051	94.027
MTEB CQADupstackMathematicaRetrieval	18.5	27.950999999999997	29.186	29.298000000000002	22.637	32.572	33.472	33.533	22.637	33.73	39.568	42.201	22.637	6.281000000000001	1.073	0.14300000000000002	18.5	46.744	72.072	N/A

Clustering Tasks

Dataset	V-Measure
MTEB ArxivClusteringP2P	48.619246083417295
MTEB ArxivClusteringS2S	43.3574067664688
MTEB BiorxivClusteringP2P	39.10510519739522
MTEB BiorxivClusteringS2S	36.84689960264385

Reranking Tasks

Dataset	MAP	MRR
MTEB AskUbuntuDupQuestions	63.06359661829253	76.15596007562766

STS Tasks

Dataset	Cosine Similarity Pearson	Cosine Similarity Spearman	Euclidean Pearson	Euclidean Spearman	Manhattan Pearson	Manhattan Spearman
MTEB BIOSSES	90.25407547368691	88.65081514968477	88.14857116664494	88.50683596540692	87.9654797992225	88.21164851646908

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