6 papers · 1 filter
Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records
Max Friedrich, Arne Köhn, Gregor Wiedemann +1
De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHRs) to be shared for…
Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings
Rami Aly, Shantanu Acharya, Alexander Ossa +3
We introduce the use of Poincaré embeddings to improve existing state-of-the-art approaches to domain-specific taxonomy induction from text as a signal for both relocating wrong hy…
Finding the way from ä to a: Sub-character morphological inflection for the SIGMORPHON 2018 Shared Task
Fynn Schröder, Marcel Kamlot, Gregor Billing +1
In this paper we describe the system submitted by UHH to the CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. We propose a neural architecture based on the…
Open Source Automatic Speech Recognition for German
Benjamin Milde, Arne Köhn
High quality Automatic Speech Recognition (ASR) is a prerequisite for speech-based applications and research. While state-of-the-art ASR software is freely available, the language…
An Empirical Analysis of the Correlation of Syntax and Prosody
Arne Köhn, Timo Baumann, Oskar Dörfler
The relation of syntax and prosody (the syntax--prosody interface) has been an active area of research, mostly in linguistics and typically studied under controlled conditions. Mor…
Incremental Natural Language Processing: Challenges, Strategies, and Evaluation
Arne Köhn
Incrementality is ubiquitous in human-human interaction and beneficial for human-computer interaction. It has been a topic of research in different parts of the NLP community, most…