Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens

• URL: http://arxiv.org/abs/2210.14011v1
• Date: Tue, 25 Oct 2022 13:31:28 GMT
• Title: Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens
• Authors: Nitish Joshi, Xiang Pan, He He
• Abstract summary: 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.
• Score: 23.41097494945868
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The term `spurious correlations' has been used in NLP to informally denote any undesirable feature-label correlations. However, a correlation can be undesirable because (i) the feature is irrelevant to the label (e.g. punctuation in a review), or (ii) the feature's effect on the label depends on the context (e.g. negation words in a review), which is ubiquitous in language tasks. In case (i), we want the model to be invariant to the feature, which is neither necessary nor sufficient for prediction. But in case (ii), even an ideal model (e.g. humans) must rely on the feature, since it is necessary (but not sufficient) for prediction. Therefore, a more fine-grained treatment of spurious features is needed to specify the desired model behavior. We formalize this distinction using a causal model and probabilities of necessity and sufficiency, which delineates the causal relations between a feature and a label. We then show that this distinction helps explain results of existing debiasing methods on different spurious features, and demystifies surprising results such as the encoding of spurious features in model representations after debiasing.

Related papers

• Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification [72.08225446179783]
  Inverse reinforcement learning aims to infer an agent's preferences from their behaviour. To do this, we need a behavioural model of how $pi$ relates to $R$. We analyse how sensitive the IRL problem is to misspecification of the behavioural model.
  arXiv  Detail & Related papers  (2024-03-11T16:09:39Z)
• Causal Feature Selection via Transfer Entropy [59.999594949050596]
  Causal discovery aims to identify causal relationships between features with observational data. We introduce a new causal feature selection approach that relies on the forward and backward feature selection procedures. We provide theoretical guarantees on the regression and classification errors for both the exact and the finite-sample cases.
  arXiv  Detail & Related papers  (2023-10-17T08:04:45Z)
• Accurate Use of Label Dependency in Multi-Label Text Classification Through the Lens of Causality [25.36416774024584]
  Multi-Label Text Classification aims to assign the most relevant labels to each given text. Label dependency may cause the model to suffer from unwanted prediction bias. We propose a CounterFactual Text (CFTC) to eliminate the correlation bias, and make causality-based predictions.
  arXiv  Detail & Related papers  (2023-10-11T15:28:44Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Uninformative Input Features and Counterfactual Invariance: Two Perspectives on Spurious Correlations in Natural Language [19.416033815407804]
  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.
  arXiv  Detail & Related papers  (2022-04-09T14:46:39Z)
• Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests [87.60900567941428]
  A spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character. We study stress testing using the tools of causal inference.
  arXiv  Detail & Related papers  (2021-05-31T14:39:38Z)
• Latent Causal Invariant Model [128.7508609492542]
  Current supervised learning can learn spurious correlation during the data-fitting process. We propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction.
  arXiv  Detail & Related papers  (2020-11-04T10:00:27Z)
• Learning Causal Models Online [103.87959747047158]
  Predictive models can rely on spurious correlations in the data for making predictions. One solution for achieving strong generalization is to incorporate causal structures in the models. We propose an online algorithm that continually detects and removes spurious features.
  arXiv  Detail & Related papers  (2020-06-12T20:49:20Z)

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.