Related papers: ProtoSiTex: Learning Semi-Interpretable Prototypes…

This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. Our model, developed as a part of the recent SemEval task, is based on fine-tuning individual language models (BERT,…

Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets in…

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground…

We propose SETI (Systematicity Evaluation of Textual Inference), a novel and comprehensive benchmark designed for evaluating pre-trained language models (PLMs) for their systematicity capabilities in the domain of textual inference.…

Extreme multi-label text classification (XMTC) refers to the problem of tagging a given text with the most relevant subset of labels from a large label set. A majority of labels only have a few training instances due to large label…

We put forward an end-to-end multi-step machine learning model which jointly labels semantic roles and the proto-roles of Dowty (1991), given a sentence and the predicates therein. Our best architecture first learns argument spans followed…

Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to…

Recent applications of deep convolutional neural networks in medical imaging raise concerns about their interpretability. While most explainable deep learning applications use post hoc methods (such as GradCAM) to generate feature…

As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep models. Post-hoc methods like GradCAM…

We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical…

Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…

When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect…

In order to reveal the rationale behind model predictions, many works have exploited providing explanations in various forms. Recently, to further guarantee readability, more and more works turn to generate sentence-level human language…

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly…

Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high…

In the context of some machine learning applications, obtaining data instances is a relatively easy process but labeling them could become quite expensive or tedious. Such scenarios lead to datasets with few labeled instances and a larger…

Studies of image captioning are shifting towards a trend of a fully end-to-end paradigm by leveraging powerful visual pre-trained models and transformer-based generation architecture for more flexible model training and faster inference…

Driving scene parsing is critical for autonomous vehicles to operate reliably in complex real-world traffic environments. To reduce the reliance on costly pixel-level annotations, synthetic datasets with automatically generated labels have…

Part-prototype networks have recently become methods of interest as an interpretable alternative to many of the current black-box image classifiers. However, the interpretability of these methods from the perspective of human users has not…

Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require interpretability. In practice, models that adapt well (e.g., deep networks) are often…