中文
相关论文

相关论文: S-SimCSE: Sampled Sub-networks for Contrastive Lea…

200 篇论文

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…

计算与语言 · 计算机科学 2022-05-19 Tianyu Gao , Xingcheng Yao , Danqi Chen

Effective sentence embeddings that capture semantic nuances and generalize well across diverse contexts are crucial for natural language processing tasks. We address this challenge by applying SimCSE (Simple Contrastive Learning of Sentence…

计算与语言 · 计算机科学 2025-01-24 Yumeng Wang , Ziran Zhou , Junjin Wang

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…

计算与语言 · 计算机科学 2022-09-13 Xing Wu , Chaochen Gao , Liangjun Zang , Jizhong Han , Zhongyuan Wang , Songlin Hu

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…

计算与语言 · 计算机科学 2023-12-25 Jiahao Xu , Wei Shao , Lihui Chen , Lemao Liu

Unsupervised sentence embedding aims to obtain the most appropriate embedding for a sentence to reflect its semantic. Contrastive learning has been attracting developing attention. For a sentence, current models utilize diverse data…

计算与语言 · 计算机科学 2022-03-03 Hao Wang , Yangguang Li , Zhen Huang , Yong Dou , Lingpeng Kong , Jing Shao

Several prior studies have suggested that word frequency biases can cause the Bert model to learn indistinguishable sentence embeddings. Contrastive learning schemes such as SimCSE and ConSERT have already been adopted successfully in…

计算与语言 · 计算机科学 2023-09-15 Pu Miao , Zeyao Du , Junlin Zhang

Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer. The constraint brought by this assumption is weak, and a good sentence…

计算与语言 · 计算机科学 2022-10-17 Xing Wu , Chaochen Gao , Zijia Lin , Jizhong Han , Zhongyuan Wang , Songlin Hu

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…

计算与语言 · 计算机科学 2022-06-07 Wei Wang , Liangzhu Ge , Jingqiao Zhang , Cheng Yang

Contrastive learning has been gradually applied to learn high-quality unsupervised sentence embedding. Among the previous un-supervised methods, the latest state-of-the-art method, as far as we know, is unsupervised SimCSE (unsup-SimCSE).…

计算与语言 · 计算机科学 2022-09-13 Xing Wu , Chaochen Gao , Yipeng Su , Jizhong Han , Zhongyuan Wang , Songlin Hu

We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sentence, where the…

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…

计算与语言 · 计算机科学 2023-10-24 Pengyue Hou , Xingyu Li

Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous studies, each embedding used for contrastive learning only…

计算与语言 · 计算机科学 2023-05-19 Hongliang He , Junlei Zhang , Zhenzhong Lan , Yue Zhang

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…

计算与语言 · 计算机科学 2022-11-14 Yau-Shian Wang , Ashley Wu , Graham Neubig

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese-network for this task, which obtains the sentence embeddings…

计算与语言 · 计算机科学 2021-09-28 Che Liu , Rui Wang , Jinghua Liu , Jian Sun , Fei Huang , Luo Si

Traditional comparative learning sentence embedding directly uses the encoder to extract sentence features, and then passes in the comparative loss function for learning. However, this method pays too much attention to the sentence body and…

计算与语言 · 计算机科学 2023-06-19 Wei Zhang , Xu Chen

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…

计算与语言 · 计算机科学 2023-10-25 Junlei Zhang , Zhenzhong Lan , Junxian He

Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on…

计算与语言 · 计算机科学 2023-09-26 Tim Schopf , Emanuel Gerber , Malte Ostendorff , Florian Matthes

Recently, SimCSE has shown the feasibility of contrastive learning in training sentence embeddings and illustrates its expressiveness in spanning an aligned and uniform embedding space. However, prior studies have shown that dense models…

计算与语言 · 计算机科学 2023-11-08 Ruize An , Chen Zhang , Dawei Song

This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks. We present the first backdoor attack framework, BadCSE, for state-of-the-art sentence…

计算与语言 · 计算机科学 2022-10-21 Xiaoyi Chen , Baisong Xin , Shengfang Zhai , Shiqing Ma , Qingni Shen , Zhonghai Wu

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…

计算与语言 · 计算机科学 2026-01-16 Kohei Oda , Po-Min Chuang , Kiyoaki Shirai , Natthawut Kertkeidkachorn
‹ 上一页 1 2 3 10 下一页 ›