Nikolai Vogler — accepted AI-conference papers

2023

Contrastive Attention Networks for Attribution of Early Modern Print

Nikolai Vogler, Kartik Goyal, Kishore PV Reddy, Elizaveta Pertseva, Samuel V. Lemley, Christopher N. Warren +2

AAAI 2023technical

In this paper, we develop machine learning techniques to identify unknown printers in early modern (c.~1500--1800) English printed books. Specifically, we focus on matching uniquely damaged character type-imprints in anonymously printed books to works with known printers in order to provide evidence…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

Simple Temporal Adaptation to Changing Label Sets: Hashtag Prediction via Dense KNN

Niloofar Mireshghallah, Nikolai Vogler, Junxian He, Omar Florez, Ahmed El-Kishky, Taylor Berg-Kirkpatrick

EMNLP 2023short main

User-generated social media data is constantly changing as new trends influence online discussion and personal information is deleted due to privacy concerns. However, traditional NLP models rely on fixed training datasets, which means they are unable to adapt to temporal change---both test distribu…

Cited by 0 Source ↗Scholar ↗

2022

Lacuna Reconstruction: Self-Supervised Pre-Training for Low-Resource Historical Document Transcription

Nikolai Vogler, Jonathan Allen, Matthew Miller, Taylor Berg-Kirkpatrick

NAACL 2022findings

We present a self-supervised pre-training approach for learning rich visual language representations for both handwritten and printed historical document transcription. After supervised fine-tuning of our pre-trained encoder representations for low-resource document transcription on two languages, (…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2017

Multi-view representation learning via gcca for multimodal analysis of Parkinson's disease

Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave, Raman Arora, Elmar Nöth, Najim Dehak, Heidi Christensen +9

ICASSP 2017accepted

Information from different bio-signals such as speech, handwriting, and gait have been used to monitor the state of Parkinson's disease (PD) patients, however, all the multimodal bio-signals may not always be available. We propose a method based on multi-view representation learning via generalized…

Cited by 0 Source ↗Scholar ↗

2017

On the impact of non-modal phonation on phonological features

Milos Cernak, Elmar Nöth, Frank Rudzicz, Heidi Christensen, Juan Rafael Orozco-Arroyave, Raman Arora +8

ICASSP 2017accepted

Different modes of vibration of the vocal folds contribute significantly to the voice quality. The neutral mode phonation, often used in a modal voice, is one against which the other modes can be contrastively described, also called non-modal phonations. This paper investigates the impact of non-mod…

Cited by 0 Source ↗Scholar ↗