Marcus Liwicki

Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference

2018 · arXiv (Cornell University)

We introduce a novel uncertainty estimation for classification tasks for Bayesian convolutional neural networks with variational inference. By normalizing the output of a Softplus function in the final layer, we estimate aleatoric and epistemic uncertainty …

Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms

2022

We present a fairly large, Potential Idiomatic Expression (PIE) dataset for Natural Language Processing (NLP) in English.The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation (WSD) and …

Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning

2021 · arXiv (Cornell University)

Building open-domain conversational systems (or chatbots) that produce convincing responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based models for the generation of natural language dialogue have demonstrated impressive performance in simulating human-like, single-turn conversations …

LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortion

2024 · arXiv (Cornell University)

Perspective distortion (PD) leads to substantial alterations in the shape, size, orientation, angles, and spatial relationships of visual elements in images. Accurately determining camera intrinsic and extrinsic parameters is challenging, making it hard to synthesize …