# ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

arXiv: https://arxiv.org/abs/2105.11741 · HTML: https://mlsanity.com/paper/2105.11741/

## Key facts

- Cited by 231 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [SentEval: An Evaluation Toolkit for Universal Sentence Representations](https://mlsanity.com/paper/1803.05449/) (2018)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations](https://mlsanity.com/paper/2006.03659/) (2020)
- [CLEAR: Contrastive Learning for Sentence Representation](https://mlsanity.com/paper/2012.15466/) (2020)
- [CERT: Contrastive Self-supervised Learning for Language Understanding](https://mlsanity.com/paper/2005.12766/) (2020)
- [Learning Distributed Representations of Sentences from Unlabelled Data](https://mlsanity.com/paper/1602.03483/) (2016)
- [An Unsupervised Sentence Embedding Method by Mutual Information Maximization](https://mlsanity.com/paper/2009.12061/) (2020)
- [A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation](https://mlsanity.com/paper/2009.13818/) (2020)
- [Adversarial Diversity and Hard Positive Generation](https://mlsanity.com/paper/1605.01775/) (2016)
- [Universal Sentence Representation Learning with Conditional Masked Language Model](https://mlsanity.com/paper/2012.14388/) (2020)
- [SLM: Learning a Discourse Language Representation with Sentence Unshuffling](https://mlsanity.com/paper/2010.16249/) (2020)
- [Cross-Thought for Sentence Encoder Pre-training](https://mlsanity.com/paper/2010.03652/) (2020)

## Built on by (most cited first, 30 of 231)

- [DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings](https://mlsanity.com/paper/2204.10298/) (2022)
- [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https://mlsanity.com/paper/2108.05542/) (2021)
- [A Survey on Data Augmentation for Text Classification](https://mlsanity.com/paper/2107.03158/) (2021)
- [A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions](https://mlsanity.com/paper/2310.14724/) (2023)
- [Towards the Generalization of Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2111.00743/) (2021)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [Understanding Contrastive Learning Requires Incorporating Inductive Biases](https://mlsanity.com/paper/2202.14037/) (2022)
- [PromptBERT: Improving BERT Sentence Embeddings with Prompts](https://mlsanity.com/paper/2201.04337/) (2022)
- [ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding](https://mlsanity.com/paper/2109.04380/) (2021)
- [SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation](https://mlsanity.com/paper/2108.04556/) (2021)
- [Anisotropy Is Inherent to Self-Attention in Transformers](https://mlsanity.com/paper/2401.12143/) (2024)
- [Cross-modal Contrastive Learning for Speech Translation](https://mlsanity.com/paper/2205.02444/) (2022)
- [Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics](https://mlsanity.com/paper/2211.09510/) (2022)
- [Debiased Contrastive Learning of Unsupervised Sentence Representations](https://mlsanity.com/paper/2205.00656/) (2022)
- [Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning](https://mlsanity.com/paper/2204.08143/) (2022)
- [GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning](https://mlsanity.com/paper/2402.16829/) (2024)
- [SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples](https://mlsanity.com/paper/2201.05979/) (2022)
- [Contrast and Generation Make BART a Good Dialogue Emotion Recognizer](https://mlsanity.com/paper/2112.11202/) (2021)
- [SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation](https://mlsanity.com/paper/2209.06664/) (2022)
- [Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks](https://mlsanity.com/paper/2307.16630/) (2023)
- [TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning](https://mlsanity.com/paper/2111.04198/) (2021)
- [BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings](https://mlsanity.com/paper/2311.05296/) (2023)
- [Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning](https://mlsanity.com/paper/2203.06875/) (2022)
- [PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings](https://mlsanity.com/paper/2201.12093/) (2022)
- [Improving Contrastive Learning of Sentence Embeddings from AI Feedback](https://mlsanity.com/paper/2305.01918/) (2023)
- [New Intent Discovery with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2205.12914/) (2022)
- [Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding](https://mlsanity.com/paper/2205.14814/) (2022)
- [SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding](https://mlsanity.com/paper/2209.06638/) (2022)
- [Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination](https://mlsanity.com/paper/2305.12256/) (2023)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)

## Abstract (arXiv)

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence representations are proved to be collapsed and thus produce a poor performance on the semantic textual similarity (STS) tasks. In this paper, we present ConSERT, a Contrastive Framework for Self-Supervised Sentence Representation Transfer, that adopts contrastive learning to fine-tune BERT in an unsupervised and effective way. By making use of unlabeled texts, ConSERT solves the collapse issue of BERT-derived sentence representations and make them more applicable for downstream tasks. Experiments on STS datasets demonstrate that ConSERT achieves an 8% relative improvement over the previous state-of-the-art, even comparable to the supervised SBERT-NLI. And when further incorporating NLI supervision, we achieve new state-of-the-art performance on STS tasks. Moreover, ConSERT obtains comparable results with only 1000 samples available, showing its robustness in data scarcity scenarios.