paper-with-me

Papers

Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings

2022-09-20 · Yiren Jian, Chongyang Gao, Soroush Vosoughi

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e., clustering sentences with semantically similar meanings and scattering others. In this work, we find the performance of Transformer models as sentence encoders can be improved by training with multi-modal multi-task losses, using unpaired examples from another modality (e.g., sentences and unrelated image/audio data). In particular, besides learning by the contrastive loss on text, our model clusters examples from a non-linguistic domain (e.g., visual/audio) with a similar contrastive loss at the same time. The reliance of our framework on unpaired non-linguistic data makes it language-agnostic, enabling it to be widely applicable beyond English NLP. Experiments on 7 semantic textual similarity benchmarks reveal that models trained with the additional non-linguistic (images/audio) contrastive objective lead to higher quality sentence embeddings. This indicates that Transformer models are able to generalize better by doing a similar task (i.e., clustering) with unpaired examples from different modalities in a multi-task fashion.

📄 PDF Abstract BibTeX arXiv:2209.09433

Code (1)

yiren-jian/NonLing-CSE 공식 구현 pytorch

Tasks

ClusteringContrastive LearningRepresentation LearningSemantic Textual SimilaritySentenceSentence Embeddings

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
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 $x$…
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…

Similar Papers 제목 키워드 기반

Non-contrastive sentence representations via self-supervision

2023-10-26 · Marco Farina, Duccio Pappadopulo

Sample contrastive methods, typically referred to simply as contrastive are the foundation of most unsupervised methods to learn text and sentence embeddings. On the other hand, a different class of self-supervised loss …

SentenceSentence Embeddings

EASE: Entity-Aware Contrastive Learning of Sentence Embedding

2022-01-16 · ACL ARR January 2022 1 · Anonymous

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities.The advantage of using entity supervision is twofold: (1) entities have been shown to…

ClusteringContrastive LearningSemantic Textual SimilaritySentence+6

Improving Contrastive Learning of Sentence Embeddings from AI Feedback

2023-05-03 · Qinyuan Cheng, Xiaogui Yang, Tianxiang Sun, Linyang Li 외

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the q…

Contrastive LearningData AugmentationSemantic Textual SimilaritySentence+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

EASE: Entity-Aware Contrastive Learning of Sentence Embedding

2022-05-09 · NAACL 2022 7 · Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka 외

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown t…

ClusteringContrastive LearningSemantic Textual SimilaritySentence+6