Heavy-tailed Representations, Text Polarity Classification & Data Augmentation

• URL: http://arxiv.org/abs/2003.11593v2
• Date: Thu, 25 Mar 2021 15:49:21 GMT
• Title: Heavy-tailed Representations, Text Polarity Classification & Data Augmentation
• Authors: Hamid Jalalzai, Pierre Colombo, Chlo\'e Clavel, Eric Gaussier, Giovanna Varni, Emmanuel Vignon, Anne Sabourin
• Abstract summary: We develop a novel method to learn a heavy-tailed embedding with desirable regularity properties. A classifier dedicated to the tails of the proposed embedding is obtained which performance outperforms the baseline. Numerical experiments on synthetic and real text data demonstrate the relevance of the proposed framework.
• Score: 11.624944730002298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation. In this paper, we develop a novel method to learn a heavy-tailed embedding with desirable regularity properties regarding the distributional tails, which allows to analyze the points far away from the distribution bulk using the framework of multivariate extreme value theory. In particular, a classifier dedicated to the tails of the proposed embedding is obtained which performance outperforms the baseline. This classifier exhibits a scale invariance property which we leverage by introducing a novel text generation method for label preserving dataset augmentation. Numerical experiments on synthetic and real text data demonstrate the relevance of the proposed framework and confirm that this method generates meaningful sentences with controllable attribute, e.g. positive or negative sentiment.

Related papers

• Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context [2.2783452228152923]
  We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text. All experiments are performed using texts written in the Mayan language Uspanteko.
  arXiv  Detail & Related papers  (2023-11-05T21:45:57Z)
• Language Model Decoding as Direct Metrics Optimization [87.68281625776282]
  Current decoding methods struggle to generate texts that align with human texts across different aspects. In this work, we frame decoding from a language model as an optimization problem with the goal of strictly matching the expected performance with human texts. We prove that this induced distribution is guaranteed to improve the perplexity on human texts, which suggests a better approximation to the underlying distribution of human texts.
  arXiv  Detail & Related papers  (2023-10-02T09:35:27Z)
• Flow Factorized Representation Learning [109.51947536586677]
  We introduce a generative model which specifies a distinct set of latent probability paths that define different input transformations. We show that our model achieves higher likelihoods on standard representation learning benchmarks while simultaneously being closer to approximately equivariant models.
  arXiv  Detail & Related papers  (2023-09-22T20:15:37Z)
• Semantic Text Compression for Classification [17.259824817932294]
  We study semantic compression for text where meanings contained in the text are conveyed to a source decoder, e.g., for classification. We propose semantic quantization and compression approaches for text where we utilize sentence embeddings and the semantic distortion metric to preserve the meaning.
  arXiv  Detail & Related papers  (2023-09-19T17:50:57Z)
• Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation [35.33340453046864]
  Chain-of-Thought Attribute Manipulation (CoTAM) is a novel approach that generates new data from existing examples. We leverage the chain-of-thought prompting to directly edit the text in three steps, (1) attribute decomposition, (2) manipulation proposal, and (3) sentence reconstruction.
  arXiv  Detail & Related papers  (2023-07-14T00:10:03Z)
• Reprint: a randomized extrapolation based on principal components for data augmentation [11.449992652644577]
  This paper presents a simple and effective hidden-space data augmentation method for imbalanced data classification. Given hidden-space representations of samples in each class, REPRINT extrapolates, in a randomized fashion, augmented examples for target class. This method involves a label refinement component which allows to synthesize new soft labels for augmented examples.
  arXiv  Detail & Related papers  (2022-04-26T01:38:47Z)
• Discriminative Attribution from Counterfactuals [64.94009515033984]
  We present a method for neural network interpretability by combining feature attribution with counterfactual explanations. We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
  arXiv  Detail & Related papers  (2021-09-28T00:53:34Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)
• A Framework to Learn with Interpretation [2.3741312212138896]
  We present a novel framework to jointly learn a predictive model and its associated interpretation model. We seek for a small-size dictionary of high level attribute functions that take as inputs the outputs of selected hidden layers. A detailed pipeline to visualize the learnt features is also developed.
  arXiv  Detail & Related papers  (2020-10-19T09:26:28Z)
• A Comparative Study on Structural and Semantic Properties of Sentence Embeddings [77.34726150561087]
  We propose a set of experiments using a widely-used large-scale data set for relation extraction. We show that different embedding spaces have different degrees of strength for the structural and semantic properties. These results provide useful information for developing embedding-based relation extraction methods.
  arXiv  Detail & Related papers  (2020-09-23T15:45:32Z)
• Building powerful and equivariant graph neural networks with structural message-passing [74.93169425144755]
  We propose a powerful and equivariant message-passing framework based on two ideas. First, we propagate a one-hot encoding of the nodes, in addition to the features, in order to learn a local context matrix around each node. Second, we propose methods for the parametrization of the message and update functions that ensure permutation equivariance.
  arXiv  Detail & Related papers  (2020-06-26T17:15:16Z)

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.