Related papers: Understanding and Mitigating Spurious Correlations…

Large scale object detection with thousands of classes introduces the problem of many contradicting false positive detections, which have to be suppressed. Class-independent non-maximum suppression has traditionally been used for this step,…

Deep neural networks often exploit *spurious* features that are present in the majority of examples within a class during training. This leads to *poor worst-group test accuracy*, i.e., poor accuracy for minority groups that lack these…

When coping with literary texts such as novels or short stories, the extraction of structured information in the form of a knowledge graph might be hindered by the huge number of possible relations between the entities corresponding to the…

Coreset selection methods have shown promise in reducing the training data size while maintaining model performance for data-efficient machine learning. However, as many datasets suffer from biases that cause models to learn spurious…

Discovering fine-grained categories from coarsely labeled data is a practical and challenging task, which can bridge the gap between the demand for fine-grained analysis and the high annotation cost. Previous works mainly focus on…

Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In…

There are different ways to define similarity for grouping similar texts into clusters, as the concept of similarity may depend on the purpose of the task. For instance, in topic extraction similar texts mean those within the same semantic…

While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if…

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods…

Discourse relation classification is an especially difficult task without explicit context markers (Prasad et al., 2008). Current approaches to implicit relation prediction solely rely on two neighboring sentences being targeted, ignoring…

Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…

Class labels used for machine learning are relatable to each other, with certain class labels being more similar to each other than others (e.g. images of cats and dogs are more similar to each other than those of cats and cars). Such…

With the large amount of data generated every day, public sentiment is a key factor for various fields, including marketing, politics, and social research. Understanding the public sentiment about different topics can provide valuable…

Recent research has shown that static word embeddings can encode word frequency information. However, little has been studied about this phenomenon and its effects on downstream tasks. In the present work, we systematically study the…

In order to maximize the applicability of sentiment analysis results, it is necessary to not only classify the overall sentiment (positive/negative) of a given document but also to identify the main words that contribute to the…

Semi-supervised learning (SSL) assumes that neighbor points lie in the same category (neighbor assumption), and points in different clusters belong to various categories (cluster assumption). Existing methods usually rely on similarity…

We introduce a data-centric hypothesis-testing framework to quantify the influence of sequentially correlated literary properties--such as thematic continuity--on textual classification tasks. Our method models label sequences as stochastic…

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…

This thesis presents two similarity-based approaches to sparse data problems. The first approach is to build soft, hierarchical clusters: soft, because each event belongs to each cluster with some probability; hierarchical, because cluster…

Applying machine learning algorithms to large-scale, text-based corpora (embeddings) presents a unique opportunity to investigate at scale how human semantic knowledge is organized and how people use it to judge fundamental relationships,…