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

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9804 - 9817 December 7-11, 2022 ©2022 Association for Computational Linguistics Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens Nitish Joshi1∗ Xiang Pan1∗ He He1,2 1Department of Computer Science, New York University 2Center for Data Science, New York University {nitish, xiangpan, hhe}@nyu.edu Abstract The term ‘spurious correlations’ has been used in NLP to informally denote any undesirable feature-label correlations. However, a correla- tion 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 neces- sary 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 suf- ficiency, which delineates the causal relations between a feature and a label. We then show that this distinction helps explain results of ex- isting debiasing methods on different spurious features, and demystifies surprising results such as the encoding of spurious features in model representations after debiasing. 1 Introduction Advancements in pre-trained language models (De- vlin et al., 2019; Radford et al., 2019) and large datasets (Rajpurkar et al., 2016; Wang et al., 2018) have enabled tremendous progress on natural lan- guage understanding (NLU). This progress has been accompanied by the concern of models rely- ing on superficial features such as negation words and lexical overlap (Poliak et al., 2018; Gururan- gan et al., 2018; McCoy et al., 2019). Despite the progress in building models robust to spurious fea- tures (Clark et al., 2019; He et al., 2019; Sagawa* et al., 2020; Veitch et al., 2021; Puli et al., 2022), the term has been used to denote any feature that ∗equal contribution Irrelevant features Speilberg’s new film is brilliant. −→ Positive ’s new film is brilliant. −→ Positive Necessary features The differential compounds to a hefty sum over time. The differential will not grow −→ Contradiction The differential will grow −→ ? Table 1: Difference between two spurious features: (a) the director name can be replaced without affecting the sentiment prediction; (b) the negation word is necessary as it is not possible to determine the label without it. the model should not rely on, as judged by domain experts. Our key observation is that a feature can be con- sidered spurious for different reasons. Compare two such features studied in the literature (Table 1): (a) director names (such as ‘Spielberg’) in senti- ment analysis (Wang and Culotta, 2020); (b) nega- tion words in natural language inference (Gururan- gan et al., 2018). We …

Content truncated to 500 words