paper-with-me

홈 › Papers

An Efficient Self-Supervised Cross-View Training For Sentence Embedding

2023-11-06 · Peerat Limkonchotiwat, Wuttikorn Ponwitayarat, Lalita Lowphansirikul, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong

Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a representation learning method such as contrastive learning. While this approach achieves impressive performance on larger PLMs, the performance rapidly degrades as the number of parameters decreases. In this paper, we propose a framework called Self-supervised Cross-View Training (SCT) to narrow the performance gap between large and small PLMs. To evaluate the effectiveness of SCT, we compare it to 5 baseline and state-of-the-art competitors on seven Semantic Textual Similarity (STS) benchmarks using 5 PLMs with the number of parameters ranging from 4M to 340M. The experimental results show that STC outperforms the competitors for PLMs with less than 100M parameters in 18 of 21 cases.

📄 PDF Abstract BibTeX arXiv:2311.03228

Code (1)

mrpeerat/sct 공식 구현 pytorch

Tasks

Contrastive LearningLanguage ModelingLanguage ModellingRepresentation LearningSemantic Textual SimilaritySentenceSentence EmbeddingSentence-EmbeddingSTS

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
[LivE@PeRson]How do I talk to a real person at Expedia? How do I talk to a real person at Expedia? To speak with a live Expedia agent, call 1 (888) 829-0881 anytime. The customer support team is available 24/7 to help with…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Improving Sentence Representations with Consensus Maximisation

2018-10-02 · ICLR 2019 5 · Shuai Tang, Virginia R. de Sa

Consensus maximisation learning can provide self-supervision when different views are available of the same data. The distributional hypothesis provides another form of useful self-supervision from adjacent sentences whi…

Self-Supervised LearningSentence

miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings

2022-11-09 · Tassilo Klein, Moin Nabi

This paper presents miCSE, a mutual information-based contrastive learning framework that significantly advances the state-of-the-art in few-shot sentence embedding. The proposed approach imposes alignment between the at…

Contrastive LearningFew-Shot LearningSelf-Supervised LearningSentence+3

Sentence embedding with contrastive multi-views learning

2019-09-25 · Antoine Simoulin

In this work, we propose a self-supervised method to learn sentence representations with an injection of linguistic knowledge. Multiple linguistic frameworks propose diverse sentence structures from which semantic meanin…

DiversitySentenceSentence EmbeddingSentence-Embedding

Revisiting Self-Training for Few-Shot Learning of Language Model

2021-10-04 · EMNLP 2021 11 · Yiming Chen, Yan Zhang, Chen Zhang, Grandee Lee 외

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training…

BenchmarkingFew-Shot LearningLanguage ModelingLanguage Modelling+5

Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations

2019-08-04 · Chanatip Saetia, Ekapol Chuangsuwanich, Tawunrat Chalothorn, Peerapon Vateekul

A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep lea…

SentenceSentence segmentation