212 citations · 741 across the 81 of their papers we have counts for
7 papers · 1 filter
Image Manipulation with Natural Language using Two-sidedAttentive Conditional Generative Adversarial Network
Dawei Zhu, Aditya Mogadala, Dietrich Klakow
Altering the content of an image with photo editing tools is a tedious task for an inexperienced user. Especially, when modifying the visual attributes of a specific object in an i…
Feature-Dependent Confusion Matrices for Low-Resource NER Labeling with Noisy Labels
Lukas Lange, Michael A. Hedderich, Dietrich Klakow
In low-resource settings, the performance of supervised labeling models can be improved with automatically annotated or distantly supervised data, which is cheap to create but ofte…
Select and Attend: Towards Controllable Content Selection in Text Generation
Xiaoyu Shen, Jun Suzuki, Kentaro Inui +3
Many text generation tasks naturally contain two steps: content selection and surface realization. Current neural encoder-decoder models conflate both steps into a black-box archit…
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
Aditya Mogadala, Marimuthu Kalimuthu, Dietrich Klakow
Interest in Artificial Intelligence (AI) and its applications has seen unprecedented growth in the last few years. This success can be partly attributed to the advancements made in…
Using Multi-Sense Vector Embeddings for Reverse Dictionaries
Michael A. Hedderich, Andrew Yates, Dietrich Klakow +1
Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings…
Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
Debjit Paul, Mittul Singh, Michael A. Hedderich +1
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount…
On the security relevance of weights in deep learning
Kathrin Grosse, Thomas A. Trost, Marius Mosbach +2
Recently, a weight-based attack on stochastic gradient descent inducing overfitting has been proposed. We show that the threat is broader: A task-independent permutation on the ini…