Methods › Natural Language Processing › Sentence Embeddings › SimCSE
SimCSE
Introduced by Tianyu Gao et al. in SimCSE: Simple Contrastive Learning of Sentence Embeddings
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SimCSE is a contrastive learning framework for generating sentence embeddings. It utilizes an unsupervised approach, which takes an input sentence and predicts itself in contrastive objective, with only standard dropout used as noise. The authors find that dropout acts as minimal “data augmentation” of hidden representations, while removing it leads to a representation collapse. Afterwards a supervised approach is used, which incorporates annotated pairs from natural language inference datasets into the contrastive framework, by using “entailment” pairs as positives and “contradiction
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 23 in the graph, strongest link: official). This answer is about arXiv:2104.08821, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2104.08821 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified (of 30 harvested samples) · 19 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 52 · with a code link: 28 · where Syntology ran a sample: 10 (7 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (10 of 52 tagged: 7 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 52 of 52, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations 15 May 2025 · 1 repository · arXiv:2505.10354
-
Revisiting Word Embeddings in the LLM Era 26 Feb 2025 · 0 repositories · arXiv:2502.19607
-
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls 16 Feb 2025 · 1 repository · arXiv:2502.11183Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)
-
2-Tier SimCSE: Elevating BERT for Robust Sentence Embeddings 23 Jan 2025 · 0 repositories · arXiv:2501.13758
-
A Comparative Study of Text Retrieval Models on DaReCzech 19 Nov 2024 · 0 repositories · arXiv:2411.12921
-
HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives 19 Nov 2024 · 0 repositories · arXiv:2411.12156
-
Deep Learning Based Dense Retrieval: A Comparative Study 27 Oct 2024 · 0 repositories · arXiv:2410.20315
-
ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings 28 Aug 2024 · 1 repository · arXiv:2409.00120
-
DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries 25 May 2024 · 1 repository · arXiv:2405.16153
-
Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings 23 Feb 2024 · 0 repositories · arXiv:2402.15153
-
Similarity-based Neighbor Selection for Graph LLMs 6 Feb 2024 · 1 repository · arXiv:2402.03720Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples) · 9 pointer-only (licence)
-
UNSEE: Unsupervised Non-contrastive Sentence Embeddings 27 Jan 2024 · 1 repository · arXiv:2401.15316Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)
-
Contrastive Learning in Distilled Models 23 Jan 2024 · 1 repository · arXiv:2401.12472
-
GYM at Qur’an QA 2023 Shared Task: Multi-Task Transfer Learning for Quranic Passage Retrieval and Question Answering with Large Language Models 7 Dec 2023 · 1 repository
-
Sparse Contrastive Learning of Sentence Embeddings 7 Nov 2023 · 0 repositories · arXiv:2311.03881
-
Japanese SimCSE Technical Report 30 Oct 2023 · 1 repository · arXiv:2310.19349
-
Non-contrastive sentence representations via self-supervision 26 Oct 2023 · 0 repositories · arXiv:2310.17690
-
Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning 17 Oct 2023 · 1 repository · arXiv:2310.10962
-
Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE 10 Oct 2023 · 1 repository · arXiv:2310.06918
-
SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels 21 Sep 2023 · 0 repositories · arXiv:2309.13080
-
DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective 14 Sep 2023 · 0 repositories · arXiv:2309.07396
-
SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings 21 Jun 2023 · 0 repositories · arXiv:2306.12280
-
CMLM-CSE: Based on Conditional MLM Contrastive Learning for Sentence Embeddings 16 Jun 2023 · 0 repositories · arXiv:2306.09594
-
BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs 6 Jun 2023 · 1 repository · arXiv:2306.03355
-
C-STS: Conditional Semantic Textual Similarity 24 May 2023 · 1 repository · arXiv:2305.15093Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 4 harvested samples) · 4 pointer-only (licence)
-
SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives 22 May 2023 · 0 repositories · arXiv:2305.13192
-
CSDR-BERT: a pre-trained scientific dataset match model for Chinese Scientific Dataset Retrieval 30 Jan 2023 · 0 repositories · arXiv:2301.12700
-
MED-SE: Medical Entity Definition-based Sentence Embedding 9 Dec 2022 · 0 repositories · arXiv:2212.04734
-
Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches 29 Nov 2022 · 2 repositories · arXiv:2211.16285
-
English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings 11 Nov 2022 · 1 repository · arXiv:2211.06127Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 5 pointer-only (licence)
-
InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings 8 Oct 2022 · 2 repositories · arXiv:2210.06432
-
SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning 8 Oct 2022 · 1 repository · arXiv:2210.03963
-
Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives 6 Jun 2022 · 1 repository · arXiv:2206.02457
-
Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval 5 Jun 2022 · 1 repository · arXiv:2206.02082Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings 21 Apr 2022 · 1 repository · arXiv:2204.10298Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 2 pointer-only (licence)
-
Generative or Contrastive? Phrase Reconstruction for Better Sentence Representation Learning 20 Apr 2022 · 0 repositories · arXiv:2204.09358
-
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning 14 Mar 2022 · 1 repository · arXiv:2203.06875
-
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings 11 Mar 2022 · 1 repository · arXiv:2203.05877Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Deep Continuous Prompt for Contrastive Learning of Sentence Embeddings 16 Jan 2022 · 0 repositories
-
Learning Monolingual Sentence Embeddings with Large-scale Parallel Translation Datasets 16 Jan 2022 · 0 repositories
-
PromptBERT: Improving BERT Sentence Embeddings with Prompts 12 Jan 2022 · 1 repository · arXiv:2201.04337Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; the one sample that ran constructed an object rather than computing a result (of 5 harvested samples) · 5 pointer-only (licence)
-
S-SimCSE: Sampled Sub-networks for Contrastive Learning of Sentence Embedding 23 Nov 2021 · 0 repositories · arXiv:2111.11750
-
A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings 16 Nov 2021 · 0 repositories
-
Control False Negative Instances In Contrastive Learning To ImproveLong-tailed Item Categorization 16 Nov 2021 · 0 repositories
-
Learning Universal Sentence Embeddings with Large-scale Parallel Translation Datasets 16 Nov 2021 · 0 repositories
-
PromptBERT: Improving BERT Sentence Embeddings with Prompts 16 Nov 2021 · 0 repositories
-
TransAug: Translate as Augmentation for Sentence Embeddings 30 Oct 2021 · 0 repositories · arXiv:2111.00157
-
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations 27 Sep 2021 · 1 repository · arXiv:2109.13059
-
ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding 9 Sep 2021 · 2 repositories · arXiv:2109.04380
-
Smoothed Contrastive Learning for Unsupervised Sentence Embedding 9 Sep 2021 · 2 repositories · arXiv:2109.04321
-
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models 19 Aug 2021 · 2 repositories · arXiv:2108.08877
-
SimCSE: Simple Contrastive Learning of Sentence Embeddings 18 Apr 2021 · 23 repositories · arXiv:2104.08821Syntology community repositories only · 17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified (of 30 harvested samples) · 19 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 53 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections