paper-with-me

홈 › Papers

Self-Guided Contrastive Learning for BERT Sentence Representations

2021-06-03 · ACL 2021 5 · Taeuk Kim, Kang Min Yoo, Sang-goo Lee

Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we propose a contrastive learning method that utilizes self-guidance for improving the quality of BERT sentence representations. Our method fine-tunes BERT in a self-supervised fashion, does not rely on data augmentation, and enables the usual [CLS] token embeddings to function as sentence vectors. Moreover, we redesign the contrastive learning objective (NT-Xent) and apply it to sentence representation learning. We demonstrate with extensive experiments that our approach is more effective than competitive baselines on diverse sentence-related tasks. We also show it is efficient at inference and robust to domain shifts.

📄 PDF Abstract BibTeX arXiv:2106.07345

Code (1)

galsang/SG-BERT 공식 구현 pytorch

Tasks

Contrastive LearningData AugmentationRepresentation LearningSentenceSentence Embeddings

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Contrastive Learning 설명 없음
Adam 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

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

2021-05-25 · ACL 2021 5 · Yuanmeng Yan, Rumei Li, Sirui Wang, Fuzheng Zhang 외

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 deriv…

Contrastive LearningSemantic Textual SimilaritySentenceSTS

CERT: Contrastive Self-supervised Learning for Language Understanding

2020-05-16 · Hongchao Fang, Sicheng Wang, Meng Zhou, Jiayuan Ding 외

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able …

Natural Language UnderstandingSelf-Supervised LearningSentenceTranslation

Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation Analysis

2021-06-01 · NAACL 2021 4 · Hirokazu Kiyomaru, Sadao Kurohashi

We propose a method to learn contextualized and generalized sentence representations using contrastive self-supervised learning. In the proposed method, a model is given a text consisting of multiple sentences. One sente…

Self-Supervised LearningSentence

SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking

2022-10-31 · Xiaotian Zhang, Hang Yan, Yu Sun, Xipeng Qiu

Due to the ambiguity of homophones, Chinese Spell Checking (CSC) has widespread applications. Existing systems typically utilize BERT for text encoding. However, CSC requires the model to account for both phonetic and gr…

Chinese Spell CheckingContrastive LearningSentence

Alleviating Over-smoothing for Unsupervised Sentence Representation

2023-05-09 · Nuo Chen, Linjun Shou, Ming Gong, Jian Pei 외

Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities. Lots of approaches based on pre-trained language models (PLMs) and contrastive learning hav…

Contrastive LearningSemantic Textual SimilaritySentence