Challenge: Existing supervised sentence embedding techniques rely on expensive human-annotated sentence pairs as the supervised signals.
Approach: They propose a semi-supervised sentence embedding framework that leverages large-scale unlabeled data.
Outcome: The proposed framework surpasses state-of-the-art methods on four domain adaptation tasks.

Similar Papers

Differentiable Data Augmentation for Contrastive Sentence Representation Learning (2022.emnlp-main)

Copied to clipboard

Challenge: a contrastive learning framework is used to fine-tune pre-trained language models with unlabeled sentences or labeled sentences.
Approach: They propose a method that makes hard positives from unlabeled sentences . they use a prefix attached to a model to allow for differentiable data augmentation .
Outcome: The proposed method yields significant improvements over existing methods under semi-supervised and supervised settings.
Contrastive Learning of Sentence Embeddings from Scratch (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to learn sentence embeddings with unlabeled data are limited due to copyright restrictions, data distribution issues, and messy formats.
Approach: They propose a contrastive learning framework that trains sentence embeddings with synthetic data.
Outcome: The proposed framework produces positive and negative annotations given unlabeled sentences and generates sentences along with their corresponding annotations from scratch.
SimCSE: Simple Contrastive Learning of Sentence Embeddings (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for learning universal sentence embeddings are based on unsupervised approaches with only dropout as noise.
Approach: They propose an unsupervised approach that takes an input sentence and predicts itself in a contrastive objective with only standard dropout used as noise.
Outcome: The proposed framework performs on par with previous supervised approaches and can produce superior sentence embeddings from unlabeled or labeled data.
Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for training contrastive learning based sentence embedding models are largely influenced by the quality of sentence pairs.
Approach: They propose a framework that decomposes LLMs into three stages for training . they propose to refine the generated content at these stages to ensure only high-quality sentence pairs are utilized to train a base contrastive learning model.
Outcome: The proposed framework surpasses ChatGPT and ChatGPP in terms of performance.
Virtual Augmentation Supported Contrastive Learning of Sentence Representations (2022.findings-acl)

Copied to clipboard

Challenge: Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain-specific knowledge.
Approach: They propose a virtual augmentation supported Contrastive Learning of sentence representations . they approximate the neighborhood of an instance via its K-nearest in-batch neighbors .
Outcome: The proposed model outperforms existing methods on a wide range of downstream tasks.
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing contrastive methods for learning universal sentence embeddings have limitations due to their over-parameterization and poor performance under domain shift settings.
Approach: They propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power of contrastive learning for sentence embeddings by combining PLMs with energy-based learning.
Outcome: Empirical results show that the proposed method improves on seven standard semantic textual similarity tasks and a domain-shifted STS task.
Hyper-CL: Conditioning Sentence Representations with Hypernetworks (2024.acl-long)

Copied to clipboard

Challenge: Existing approaches to sentence embeddings do not capture fine-grained semantics of sentences.
Approach: They propose a method that integrates hypernetworks with contrastive learning to generate conditioned sentence representations.
Outcome: The proposed method narrows the performance gap with the bi-encoder architecture while maintaining the time efficiency characteristic of the tri-encoding approach.
GASE: Generatively Augmented Sentence Encoding (2025.findings-emnlp)

Copied to clipboard

Challenge: Generatively Augmented Sentence Encoding variates the input text by paraphrasing, summarizing, or extracting keywords, followed by pooling the original and synthetic embeddings.
Approach: They propose a training-free approach to improve sentence embeddings by applying generative text models for data augmentation at inference time.
Outcome: The proposed approach does not require access to model parameters or computational resources typically required for fine-tuning state-of-the-art models.
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer (2021.acl-long)

Copied to clipboard

Challenge: Existing BERT-based pre-trained language models achieve high performance on many downstream tasks, but native derived sentence representations are collapsed and thus poor performance on semantic textual similarity (STS) tasks.
Approach: They propose a framework for self-supervised Sentence Representation Transfer that adopts contrastive learning to fine-tune BERT in an unsupervised way.
Outcome: The proposed framework improves on the BERT-derived representations by 8% on STS datasets and shows robustness in data scarcity scenarios.
SumCSE: Summary as a transformation for Contrastive Learning (2024.findings-naacl)

Copied to clipboard

Challenge: Sentence embedding models are typically trained using contrastive learning (CL) using human annotations directly or by repurposing other annotated datasets.
Approach: They propose to use generative language models to generate CL data using annotated data.
Outcome: The proposed method outperforms the previous best unsupervised method by 1.8 points and SimCSE, a strong supervised baseline by 0.3 points on the semantic text similarity (STS) benchmark.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations