paper-with-me

홈 › Papers

Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Tasks

2021-10-10 · NAACL 2022 7 · Anton Chernyavskiy, Dmitry Ilvovsky, Pavel Kalinin, Preslav Nakov

The use of contrastive loss for representation learning has become prominent in computer vision, and it is now getting attention in Natural Language Processing (NLP). Here, we explore the idea of using a batch-softmax contrastive loss when fine-tuning large-scale pre-trained transformer models to learn better task-specific sentence embeddings for pairwise sentence scoring tasks. We introduce and study a number of variations in the calculation of the loss as well as in the overall training procedure; in particular, we find that data shuffling can be quite important. Our experimental results show sizable improvements on a number of datasets and pairwise sentence scoring tasks including classification, ranking, and regression. Finally, we offer detailed analysis and discussion, which should be useful for researchers aiming to explore the utility of contrastive loss in NLP.

📄 PDF Abstract BibTeX arXiv:2110.15725

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSentenceSentence Embeddings

Similar Papers 제목 키워드 기반

Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Tasks

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

The use of contrastive loss for representation learning has become prominent in computer vision, and it is now getting attention in Natural Language Processing (NLP). Here, we explore the idea of using a batch-softmax co…

Representation LearningSentenceSentence Embeddings

Sigmoid Loss for Language Image Pre-Training

2023-03-27 · ICCV 2023 1 · Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer

We propose a simple pairwise Sigmoid loss for Language-Image Pre-training (SigLIP). Unlike standard contrastive learning with softmax normalization, the sigmoid loss operates solely on image-text pairs and does not requi…

Contrastive LearningDisentanglementImage-to-Text RetrievalZero-shot Text-to-Image Retrieval

BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation

2025-08-09 · Christos Tsirigotis, Vaibhav Adlakha, Joao Monteiro, Aaron Courville 외 arxiv

Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world relevance often exists on a continuum, a…

Contrastive Learning

NBC-Softmax : Darkweb Author fingerprinting and migration tracking

2022-12-15 · Gayan K. Kulatilleke, Shekhar S. Chandra, Marius Portmann

Metric learning aims to learn distances from the data, which enhances the performance of similarity-based algorithms. An author style detection task is a metric learning problem, where learning style features with small …

Metric LearningStyle Detection

Softmax GAN

2017-04-20 · Min Lin

Softmax GAN is a novel variant of Generative Adversarial Network (GAN). The key idea of Softmax GAN is to replace the classification loss in the original GAN with a softmax cross-entropy loss in the sample space of one s…

Generative Adversarial Network