Discriminative Learning with Natural Annotations: Word Segmentation as a Case Study

Morphological Segmentation Inside-Out

Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- e…

Keyboard Logs as Natural Annotations for Word Segmentation

Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty

Weakly-supervised learning (WSL) has recently triggered substantial interest as it mitigates the lack of pixel-wise annotations. Given global image labels, WSL methods yield pixel-level predictions (segmentations), which…

Nonparametric Bayesian Semi-supervised Word Segmentation

This paper presents a novel hybrid generative/discriminative model of word segmentation based on nonparametric Bayesian methods. Unlike ordinary discriminative word segmentation which relies only on labeled data, our sem…

Unsupervised Keyword Extraction for Full-sentence VQA

In the majority of the existing Visual Question Answering (VQA) research, the answers consist of short, often single words, as per instructions given to the annotators during dataset construction. This study envisions a …