Differentiable Data Augmentation for Contrastive Sentence Representation Learning

• URL: http://arxiv.org/abs/2210.16536v1
• Date: Sat, 29 Oct 2022 08:57:45 GMT
• Title: Differentiable Data Augmentation for Contrastive Sentence Representation Learning
• Authors: Tianduo Wang and Wei Lu
• Abstract summary: The proposed method yields significant improvements over existing methods under both semi-supervised and supervised settings. Our experiments under a low labeled data setting also show that our method is more label-efficient than the state-of-the-art contrastive learning methods.
• Score: 6.398022050054328
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive learning framework has shown its superiority on sentence representation learning over previous methods, the potential of such a framework is under-explored so far due to the simple method it used to construct positive pairs. Motivated by this, we propose a method that makes hard positives from the original training examples. A pivotal ingredient of our approach is the use of prefix that is attached to a pre-trained language model, which allows for differentiable data augmentation during contrastive learning. Our method can be summarized in two steps: supervised prefix-tuning followed by joint contrastive fine-tuning with unlabeled or labeled examples. Our experiments confirm the effectiveness of our data augmentation approach. The proposed method yields significant improvements over existing methods under both semi-supervised and supervised settings. Our experiments under a low labeled data setting also show that our method is more label-efficient than the state-of-the-art contrastive learning methods.

Related papers

• Deep Learning in Medical Image Registration: Magic or Mirage? [18.620739011646123]
  We make an explicit correspondence between the distribution of per-pixel intensity and labels, and the performance of classical registration methods. We show that learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods.
  arXiv  Detail & Related papers  (2024-08-11T18:20:08Z)
• DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning [59.4644086610381]
  We propose a novel denoising objective that inherits from another perspective, i.e., the intra-sentence perspective. By introducing both discrete and continuous noise, we generate noisy sentences and then train our model to restore them to their original form. Our empirical evaluations demonstrate that this approach delivers competitive results on both semantic textual similarity (STS) and a wide range of transfer tasks.
  arXiv  Detail & Related papers  (2024-01-24T17:48:45Z)
• Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework [68.04940365847543]
  We propose a semi-supervised sentence embedding framework, GenSE, that effectively leverages large-scale unlabeled data. Our method include three parts: 1) Generate: A generator/discriminator model is jointly trained to synthesize sentence pairs from open-domain unlabeled corpus; 2) Discriminate: Noisy sentence pairs are filtered out by the discriminator to acquire high-quality positive and negative sentence pairs; 3) Contrast: A prompt-based contrastive approach is presented for sentence representation learning with both annotated and synthesized data.
  arXiv  Detail & Related papers  (2022-10-30T10:15:21Z)
• Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives [17.90820242798732]
  Unsupervised contrastive learning methods still lag far behind the supervised counterparts. We propose switch-case augmentation to flip the case of the first letter of randomly selected words in a sentence. For negative samples, we sample hard negatives from the whole dataset based on a pre-trained language model.
  arXiv  Detail & Related papers  (2022-06-06T09:46:12Z)
• Conditional Supervised Contrastive Learning for Fair Text Classification [59.813422435604025]
  We study learning fair representations that satisfy a notion of fairness known as equalized odds for text classification via contrastive learning. Specifically, we first theoretically analyze the connections between learning representations with a fairness constraint and conditional supervised contrastive objectives.
  arXiv  Detail & Related papers  (2022-05-23T17:38:30Z)
• On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation [23.72825603188359]
  We can improve the interpretability of explanations by allowing arbitrary text sequences as the explanation unit. We propose a semantic-based evaluation metric that can better align with humans' judgment of explanations.
  arXiv  Detail & Related papers  (2021-06-09T00:49:56Z)
• Incremental False Negative Detection for Contrastive Learning [95.68120675114878]
  We introduce a novel incremental false negative detection for self-supervised contrastive learning. During contrastive learning, we discuss two strategies to explicitly remove the detected false negatives. Our proposed method outperforms other self-supervised contrastive learning frameworks on multiple benchmarks within a limited compute.
  arXiv  Detail & Related papers  (2021-06-07T15:29:14Z)
• Scalable Personalised Item Ranking through Parametric Density Estimation [53.44830012414444]
  Learning from implicit feedback is challenging because of the difficult nature of the one-class problem. Most conventional methods use a pairwise ranking approach and negative samplers to cope with the one-class problem. We propose a learning-to-rank approach, which achieves convergence speed comparable to the pointwise counterpart.
  arXiv  Detail & Related papers  (2021-05-11T03:38:16Z)
• Constructing Contrastive samples via Summarization for Text Classification with limited annotations [46.53641181501143]
  We propose a novel approach to constructing contrastive samples for language tasks using text summarization. We use these samples for supervised contrastive learning to gain better text representations with limited annotations. Experiments on real-world text classification datasets (Amazon-5, Yelp-5, AG News) demonstrate the effectiveness of the proposed contrastive learning framework.
  arXiv  Detail & Related papers  (2021-04-11T20:13:24Z)
• Unsupervised Document Embedding via Contrastive Augmentation [48.71917352110245]
  We present a contrasting learning approach with data augmentation techniques to learn document representations in unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and pretraining, we hypothesize that high-quality document embedding should be invariant to diverse paraphrases. Our method can decrease the classification error rate by up to 6.4% over the SOTA approaches on the document classification task, matching or even surpassing fully-supervised methods.
  arXiv  Detail & Related papers  (2021-03-26T15:48:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.