Related papers: SCENE: Self-Labeled Counterfactuals for Extrapolat…

Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…

Relation extraction (RE) aims to extract relations from sentences and documents. Existing relation extraction models typically rely on supervised machine learning. However, recent studies showed that many RE datasets are incompletely…

Counterfactual Explanations (CEs) help address the question: How can the factors that influence the prediction of a predictive model be changed to achieve a more favorable outcome from a user's perspective? Thus, they bear the potential to…

Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the…

Matching model is essential for Image-Text Retrieval framework. Existing research usually train the model with a triplet loss and explore various strategy to retrieve hard negative sentences in the dataset. We argue that current…

Distantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB). Due to the incompleteness of current KBs, sentences implying certain relations may be annotated as N/A…

Recent works have shown that supervised models often exploit data artifacts to achieve good test scores while their performance severely degrades on samples outside their training distribution. Contrast sets (Gardneret al., 2020) quantify…

The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…

Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…

Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While…

Learning-based autonomous driving systems are trained mostly on incident-free data, offering little guidance near safety-performance boundaries. Real crash reports contain precisely the contrastive evidence needed, but they are hard to use:…

Unlike traditional supervised learning, in many settings only partial feedback is available. We may only observe outcomes for the chosen actions, but not the counterfactual outcomes associated with other alternatives. Such settings…

Despite Visual Question Answering (VQA) has realized impressive progress over the last few years, today's VQA models tend to capture superficial linguistic correlations in the train set and fail to generalize to the test set with different…

We propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE). Our method leverages recent progress in large language modeling and text-based image editing to…

Distant supervision for relation extraction provides uniform bag labels for each sentence inside the bag, while accurate sentence labels are important for downstream applications that need the exact relation type. Directly using bag labels…

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the use of human-annotated natural language inference (NLI) data…

Distantly supervision automatically generates plenty of training samples for relation extraction. However, it also incurs two major problems: noisy labels and imbalanced training data. Previous works focus more on reducing wrongly labeled…