Space Decomposition for Sentence Embedding

• URL: http://arxiv.org/abs/2406.03125v1
• Date: Wed, 5 Jun 2024 10:20:10 GMT
• Title: Space Decomposition for Sentence Embedding
• Authors: Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Ekapol Chuangsuwanich, Sarana Nutanong,
• Abstract summary: This paper introduces a novel embedding space decomposition method called MixSP. It is designed to distinguish and rank upper-range and lower-range samples accurately. The experimental results demonstrate that MixSP decreased the overlap representation between upper-range and lower-range classes significantly.
• Score: 12.538707746802853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Determining sentence pair similarity is crucial for various NLP tasks. A common technique to address this is typically evaluated on a continuous semantic textual similarity scale from 0 to 5. However, based on a linguistic observation in STS annotation guidelines, we found that the score in the range [4,5] indicates an upper-range sample, while the rest are lower-range samples. This necessitates a new approach to treating the upper-range and lower-range classes separately. In this paper, we introduce a novel embedding space decomposition method called MixSP utilizing a Mixture of Specialized Projectors, designed to distinguish and rank upper-range and lower-range samples accurately. The experimental results demonstrate that MixSP decreased the overlap representation between upper-range and lower-range classes significantly while outperforming competitors on STS and zero-shot benchmarks.

Related papers

• On high-dimensional modifications of the nearest neighbor classifier [0.0]
  In this article, we discuss some of these existing methods and propose some new ones. We analyze several simulated and benchmark datasets to compare the empirical performances of proposed methods with some of the existing ones.
  arXiv  Detail & Related papers  (2024-07-06T17:53:53Z)
• Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning [59.44422468242455]
  We propose a novel method dubbed ShrinkMatch to learn uncertain samples. For each uncertain sample, it adaptively seeks a shrunk class space, which merely contains the original top-1 class. We then impose a consistency regularization between a pair of strongly and weakly augmented samples in the shrunk space to strive for discriminative representations.
  arXiv  Detail & Related papers  (2023-08-13T14:05:24Z)
• Structured Voronoi Sampling [61.629198273926676]
  In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods. We name our gradient-based technique Structured Voronoi Sampling (SVS) In a controlled generation task, SVS is able to generate fluent and diverse samples while following the control targets significantly better than other methods.
  arXiv  Detail & Related papers  (2023-06-05T17:32:35Z)
• Deep Metric Learning Assisted by Intra-variance in A Semi-supervised View of Learning [0.0]
  Deep metric learning aims to construct an embedding space where samples of the same class are close to each other, while samples of different classes are far away from each other. This paper designs a self-supervised generative assisted ranking framework that provides a semi-supervised view of intra-class variance learning scheme for typical supervised deep metric learning.
  arXiv  Detail & Related papers  (2023-04-21T13:30:32Z)
• Local overlap reduction procedure for dynamic ensemble selection [13.304462985219237]
  Class imbalance is a characteristic known for making learning more challenging for classification models. We propose a DS technique which attempts to minimize the effects of the local class overlap during the classification procedure. Experimental results show that the proposed technique can significantly outperform the baseline.
  arXiv  Detail & Related papers  (2022-06-16T21:31:05Z)
• Imbalanced Classification via a Tabular Translation GAN [4.864819846886142]
  We present a model based on Generative Adversarial Networks which uses additional regularization losses to map majority samples to corresponding synthetic minority samples. We show that the proposed method improves average precision when compared to alternative re-weighting and oversampling techniques.
  arXiv  Detail & Related papers  (2022-04-19T06:02:53Z)
• Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond [63.59034509960994]
  We study shuffling-based variants: minibatch and local Random Reshuffling, which draw gradients without replacement. For smooth functions satisfying the Polyak-Lojasiewicz condition, we obtain convergence bounds which show that these shuffling-based variants converge faster than their with-replacement counterparts. We propose an algorithmic modification called synchronized shuffling that leads to convergence rates faster than our lower bounds in near-homogeneous settings.
  arXiv  Detail & Related papers  (2021-10-20T02:25:25Z)
• A Novel Adaptive Minority Oversampling Technique for Improved Classification in Data Imbalanced Scenarios [23.257891827728827]
  Imbalance in the proportion of training samples belonging to different classes often poses performance degradation of conventional classifiers. We propose a novel three step technique to address imbalanced data.
  arXiv  Detail & Related papers  (2021-03-24T09:58:02Z)
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
  We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
  arXiv  Detail & Related papers  (2021-03-24T07:26:07Z)
• Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning [58.2091760793799]
  We propose a novel contrastive prototype learning with augmented embeddings (CPLAE) model. With a class prototype as an anchor, CPL aims to pull the query samples of the same class closer and those of different classes further away. Extensive experiments on several benchmarks demonstrate that our proposed CPLAE achieves new state-of-the-art.
  arXiv  Detail & Related papers  (2021-01-23T13:22:44Z)
• Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation [105.33409035876691]
  This paper explores the problem of multi-view spectral clustering (MVSC) based on tensor low-rank modeling. We design a novel structured tensor low-rank norm tailored to MVSC. We show that the proposed method outperforms state-of-the-art methods to a significant extent.
  arXiv  Detail & Related papers  (2020-04-30T11:52:12Z)

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.