Related papers: AugCSE: Contrastive Sentence Embedding with Divers…
We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a…
In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the…
Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework. SetCSE employs sets to represent complex semantics and incorporates well-defined operations for structured information querying under…
Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art…
We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…
This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive…
Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain specific knowledge. This challenge is magnified in natural language processing where no general rules exist for…
Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requires supervised cross-lingual parallel sentences. In this…
Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…
While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for…
Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the use of human-annotated natural language inference (NLI) data…
The recent success of SimCSE has greatly advanced state-of-the-art sentence representations. However, the original formulation of SimCSE does not fully exploit the potential of hard negative samples in contrastive learning. This study…
Contrastive learning has been attracting much attention for learning unsupervised sentence embeddings. The current state-of-the-art unsupervised method is the unsupervised SimCSE (unsup-SimCSE). Unsup-SimCSE takes dropout as a minimal data…
Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings. However, the unsupervised contrastive learning methods still lag far behind the supervised…
Sentence embedding methods have made remarkable progress, yet they still struggle to capture the implicit semantics within sentences. This can be attributed to the inherent limitations of conventional sentence embedding methods that assign…
Unsupervised relation extraction (URE) aims to extract relations between named entities from raw text without requiring manual annotations or pre-existing knowledge bases. In recent studies of URE, researchers put a notable emphasis on…
Data augmentation methods for Natural Language Processing tasks are explored in recent years, however they are limited and it is hard to capture the diversity on sentence level. Besides, it is not always possible to perform data…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
Contrastive learning has been studied for improving the performance of learning sentence embeddings. The current state-of-the-art method is the SimCSE, which takes dropout as the data augmentation method and feeds a pre-trained transformer…
Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous…