CoChat

Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual

Open access
He, He, Zha, Sheng, Wang, Haohan · 2019 · Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
Cited by 157

The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.

Abstract

Statistical natural language inference (NLI) models are susceptible to learning dataset bias: superficial cues that happen to associate with the label on a particular dataset, but are not useful in general, e.g., negation words indicate contradiction.As exposed by several recent challenge datasets, these models perform poorly when such association is absent, e.g., predicting that "I love dogs."contradicts "I don't love cats.".Our goal is to design learning algorithms that guard against known dataset bias.We formalize the concept of dataset bias under the framework of distribution shift and present a simple debiasing algorithm based on residual fitting, which we call DRiFt.We first learn a biased model that only uses features that are known to relate to dataset bias.Then, we train a debiased model that fits to the residual of the biased model, focusing on examples that cannot be predicted well by biased features only.We use DRiFt to train three high-performing NLI models on two benchmark datasets, SNLI and MNLI.Our debiased models achieve significant gains over baseline models on two challenge test sets, while maintaining reasonable performance on the original test sets. 1 1 Code is available at https://github.com/ hhexiy/debiased.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/d19-6115

Cites

21 of 21 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 21 references

Cited by

See all 157

Metadata

Authors
He, H., Zha, S., & Wang, H.
Venue
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
Published
2019
Pages
132-142
OpenAlex
W2984256198
Cited by
157
References
21
FWCI
9.62
Type
conference paper
Language
en
Open access
gold

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual. https://app.cochat.ai/papers/10.18653/v1/d19-6115
The paper
He, H., Zha, S., & Wang, H. (2019). Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual. Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019). https://doi.org/10.18653/v1/d19-6115

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.