Papers with Code · CC BY-SA 4.0

Semantic Textual Similarity

324 평가 기록 24 datasets

Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.

Image source: Learning Semantic Textual Similarity from Conversations

논문

Scaling Sentence Embeddings with Large Language Models

2307.16645 2023-07-31 이 페이지의 평가 6건

Spearman Correlation: 0.8585

AnglE-optimized Text Embeddings

2309.12871 2023-09-22 이 페이지의 평가 5건

Spearman Correlation: 0.8689

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

2109.13059 2021-09-27 이 페이지의 평가 5건

Spearman Correlation: 0.8194

MURAL: Multimodal, Multitask Retrieval Across Languages

2109.05125 2021-09-10 이 페이지의 평가 3건

avg ± std: 74.5 ± 0.4

DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

2204.10298 2022-04-21 이 페이지의 평가 2건

Spearman Correlation: 0.7647

Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders

2104.08027 2021-04-16 이 페이지의 평가 2건

Spearman Correlation: 0.732

Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning

2203.06875 2022-03-14 이 페이지의 평가 2건

Spearman Correlation: 0.8381

An Unsupervised Sentence Embedding Method by Mutual Information Maximization

2009.12061 2020-09-25 이 페이지의 평가 1건

Spearman Correlation: 0.6121

Generating Datasets with Pretrained Language Models

2104.07540 2021-04-15 이 페이지의 평가 1건

Spearman Correlation: 0.7125

On the Sentence Embeddings from Pre-trained Language Models

2011.05864 2020-11-02 이 페이지의 평가 1건

Spearman Correlation: 0.6942

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

1908.10084 2019-08-27 이 페이지의 평가 1건

Spearman Correlation: 0.7490000000000001

SimCSE: Simple Contrastive Learning of Sentence Embeddings

2104.08821 2021-04-18 이 페이지의 평가 1건

Spearman Correlation: 0.8236