Related papers: Label Forensics: Interpreting Hard Labels in Black…
In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector belongs to at least one group. Then, instead of the true label…
The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone…
Sentence embeddings are central to modern NLP and AI systems, yet little is known about their internal structure. While we can compare these embeddings using measures such as cosine similarity, the contributing features are not…
Deployed machine learning systems must continuously evolve as data, architectures, and regulations change, often without access to original training data or model internals. In such settings, black-box copying provides a practical…
Unravelling hidden patterns in datasets is a classical problem with many potential applications. In this paper, we present a challenge whose objective is to discover nonlinear relationships in noisy cloud of points. If a set of point…
Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum entries. Understanding and extracting information from large documents like legal briefs,…
Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel…
Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core…
Text Classification is one of the fundamental tasks in natural language processing, which requires an agent to determine the most appropriate category for input sentences. Recently, deep neural networks have achieved impressive performance…
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to…
Distance-based unsupervised text classification is a method within text classification that leverages the semantic similarity between a label and a text to determine label relevance. This method provides numerous benefits, including fast…
Deep neural networks learn fragile "shortcut" features, rendering them difficult to interpret (black box) and vulnerable to adversarial attacks. This paper proposes semantic features as a general architectural solution to this problem. The…
Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these…
We present a novel and scalable label embedding framework for large-scale multi-label learning a.k.a ExMLDS (Extreme Multi-Label Learning using Distributional Semantics). Our approach draws inspiration from ideas rooted in distributional…
Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation. Prior zero-label…
We present a new perspective on the popular multi-class algorithmic techniques of one-vs-all and error correcting output codes. Rather than studying the behavior of these techniques for supervised learning, we establish a connection between…
Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised…
We introduce the \textbf{Concept Field} of a text corpus: a local drift field with pointwise uncertainty, estimated in sentence-embedding space from the deltas between consecutive sentences. Given a candidate sentence transition, we score…
Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…