Uninformative Input Features and Counterfactual Invariance: Two Perspectives on Spurious Correlations in Natural Language

• URL: http://arxiv.org/abs/2204.04487v1
• Date: Sat, 9 Apr 2022 14:46:39 GMT
• Title: Uninformative Input Features and Counterfactual Invariance: Two Perspectives on Spurious Correlations in Natural Language
• Authors: Jacob Eisenstein
• Abstract summary: Spurious correlations are a threat to the trustworthiness of natural language processing systems. This paper analyzes three distinct conditions that can give rise to feature-label correlations in a simple PCFG. Because input features will be individually correlated with labels in all but very rare circumstances, domain knowledge must be applied to identify spurious correlations that pose genuine robustness threats.
• Score: 19.416033815407804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spurious correlations are a threat to the trustworthiness of natural language processing systems, motivating research into methods for identifying and eliminating them. Gardner et al (2021) argue that the compositional nature of language implies that \emph{all} correlations between labels and individual input features are spurious. This paper analyzes this proposal in the context of a toy example, demonstrating three distinct conditions that can give rise to feature-label correlations in a simple PCFG. Linking the toy example to a structured causal model shows that (1) feature-label correlations can arise even when the label is invariant to interventions on the feature, and (2) feature-label correlations may be absent even when the label is sensitive to interventions on the feature. Because input features will be individually correlated with labels in all but very rare circumstances, domain knowledge must be applied to identify spurious correlations that pose genuine robustness threats.

Related papers

• Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation [26.544938760265136]
  Deep neural classifiers rely on spurious correlations between spurious attributes of inputs and targets to make predictions. We propose a self-guided spurious correlation mitigation framework. We show that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori.
  arXiv  Detail & Related papers  (2024-05-06T17:12:21Z)
• Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models [16.328341121232484]
  We apply causal effect estimation strategies to measure the effect of context interventions. We investigate robustness to irrelevant changes and sensitivity to impactful changes of Transformers.
  arXiv  Detail & Related papers  (2024-04-03T10:22:35Z)
• Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis [69.07674653828565]
  Machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. In this paper, we examine the implications of spurious correlations through a novel perspective called neighborhood analysis. We propose a family of regularization methods, NFL (doN't Forget your Language) to mitigate spurious correlations in text classification.
  arXiv  Detail & Related papers  (2023-05-23T03:55:50Z)
• Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens [23.41097494945868]
  The term spurious correlations' has been used in NLP to informally denote any undesirable feature-label correlations. We formalize this distinction using a causal model and probabilities of necessity and sufficiency.
  arXiv  Detail & Related papers  (2022-10-25T13:31:28Z)
• Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation [32.66196135141696]
  Features with varying relationships to the label are nuisances. Models that exploit nuisance-label relationships face performance degradation when these relationships change. We develop an approach to use knowledge about the semantics by corrupting them in data.
  arXiv  Detail & Related papers  (2022-10-04T01:40:31Z)
• Fairness and robustness in anti-causal prediction [73.693135253335]
  Robustness to distribution shift and fairness have independently emerged as two important desiderata required of machine learning models. While these two desiderata seem related, the connection between them is often unclear in practice. By taking this perspective, we draw explicit connections between a common fairness criterion - separation - and a common notion of robustness.
  arXiv  Detail & Related papers  (2022-09-20T02:41:17Z)
• Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition [48.5398871460388]
  We propose a novel Contextual Latent Generative Model (Context-LGM), which considers the object-context relation and models it in a hierarchical manner. To infer contextual features, we reformulate the objective function of Variational Auto-Encoder (VAE), where contextual features are learned as a posterior conditioned distribution on the object. The effectiveness of our method is verified by state-of-the-art performance on two context-aware object recognition tasks.
  arXiv  Detail & Related papers  (2021-10-08T11:31:58Z)
• Label Distribution Amendment with Emotional Semantic Correlations for Facial Expression Recognition [69.18918567657757]
  We propose a new method that amends the label distribution of each facial image by leveraging correlations among expressions in the semantic space. By comparing semantic and task class-relation graphs of each image, the confidence of its label distribution is evaluated. Experimental results demonstrate the proposed method is more effective than compared state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-07-23T07:46:14Z)
• Measuring Association Between Labels and Free-Text Rationales [60.58672852655487]
  In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance. We demonstrate that pipelines, existing models for faithful extractive rationalization on information-extraction style tasks, do not extend as reliably to "reasoning" tasks requiring free-text rationales. We turn to models that jointly predict and rationalize, a class of widely used high-performance models for free-text rationalization whose faithfulness is not yet established.
  arXiv  Detail & Related papers  (2020-10-24T03:40:56Z)
• Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training [49.9995628166064]
  We propose CTEG, a model equipped with two mechanisms to learn to decouple easily-confused relations. On the one hand, an EGA mechanism is introduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations.
  arXiv  Detail & Related papers  (2020-10-21T11:07:53Z)
• Identifying Spurious Correlations for Robust Text Classification [9.457737910527829]
  We propose a method to distinguish spurious and genuine correlations in text classification. We use features derived from treatment effect estimators to distinguish spurious correlations from "genuine" ones. Experiments on four datasets suggest that using this approach to inform feature selection also leads to more robust classification.
  arXiv  Detail & Related papers  (2020-10-06T03:49:22Z)

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.