Related papers: Robustifying Sentiment Classification by Maximally…

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with…

While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that…

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

The reliance of text classifiers on spurious correlations can lead to poor generalization at deployment, raising concerns about their use in safety-critical domains such as healthcare. In this work, we propose to use counterfactual data…

Target-oriented multimodal sentiment classification seeks to predict sentiment polarity for specific targets from image-text pairs. While existing works achieve competitive performance, they often over-rely on textual content and fail to…

Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due…

Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task. Counterfactual data augmentations provide a general way of (approximately) achieving representations that…

In this paper, we conduct experiment to analyze whether models can classify offensive texts better with the help of sentiment. We conduct this experiment on the SemEval 2019 task 6, OLID, dataset. First, we utilize pre-trained language…

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

What are the limits of automated Twitter sentiment classification? We analyze a large set of manually labeled tweets in different languages, use them as training data, and construct automated classification models. It turns out that the…

Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language…

Existing studies on multimodal sentiment analysis heavily rely on textual modality and unavoidably induce the spurious correlations between textual words and sentiment labels. This greatly hinders the model generalization ability. To…

We describe a bootstrapping algorithm to learn from partially labeled data, and the results of an empirical study for using it to improve performance of sentiment classification using up to 15 million unlabeled Amazon product reviews. Our…

Multi-emotion sentiment classification is a natural language processing (NLP) problem with valuable use cases on real-world data. We demonstrate that large-scale unsupervised language modeling combined with finetuning offers a practical…

The brittleness of finetuned language model performance on out-of-distribution (OOD) test samples in unseen domains has been well-studied for English, yet is unexplored for multi-lingual models. Therefore, we study generalization to OOD…

Two fundamental requirements for the deployment of machine learning models in safety-critical systems are to be able to detect out-of-distribution (OOD) data correctly and to be able to explain the prediction of the model. Although…

In this work, we tackle a problem of speech emotion classification. One of the issues in the area of affective computation is that the amount of annotated data is very limited. On the other hand, the number of ways that the same emotion can…

While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a challenge. Most existing…

Since state-of-the-art approaches to offensive language detection rely on supervised learning, it is crucial to quickly adapt them to the continuously evolving scenario of social media. While several approaches have been proposed to tackle…

Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a…