• Publications
  • Influence
Adapting SimpleNLG to German
TLDR
This paper describes SimpleNLG for German, a surface realisation engine for German based on Simple NLG (Gatt and Reiter, 2009). Expand
  • 31
  • 7
  • PDF
(Semi-)Automatic Normalization of Historical Texts using Distance Measures and the Norma tool
Historical texts typically show a high degree of variance in spelling. Normalization of variant word forms to their modern spellings can greatly benefit further processing of the data, e.g., POSExpand
  • 32
  • 6
  • PDF
Rule-Based Normalization of Historical Texts
TLDR
We describe an unsupervised, rulebased approach which maps historical wordforms to their modern counterparts with a high success rate. Expand
  • 29
  • 3
  • PDF
Learning attention for historical text normalization by learning to pronounce
TLDR
We propose several novel encoder-decoder architectures, including a multi-task learning (MTL) architecture using a grapheme-to-phoneme dictionary as auxiliary data, pushing the state-of-the-art by an absolute 2% increase in performance. Expand
  • 24
  • 3
  • PDF
CorA: A web-based annotation tool for historical and other non-standard language data
TLDR
We present CorA, a web-based annotation tool for manual annotation of historical and other non-standard language data. Expand
  • 19
  • 3
  • PDF
Improving historical spelling normalization with bi-directional LSTMs and multi-task learning
TLDR
We present an approach to historical spelling normalization using bi-directional long short-term memory networks and showed that it outperforms a CRF baseline and the Norma tool by Bollmann (2012) for almost all of the texts in our dataset. Expand
  • 39
  • 2
  • PDF
POS Tagging for Historical Texts with Sparse Training Data
TLDR
This paper presents a method for part-ofspeech tagging of historical data and evaluates it on texts from different corpora of historical German (15th–18th century). Expand
  • 17
  • 2
  • PDF
A Large-Scale Comparison of Historical Text Normalization Systems
TLDR
This paper presents the largest study of historical text normalization done so far. Expand
  • 22
  • 1
  • PDF
Applying Rule-Based Normalization to Different Types of Historical Texts - An Evaluation
TLDR
This paper deals with normalization of language data from Early New High German. Expand
  • 19
  • 1
  • PDF
The CLIN27 Shared Task: Translating Historical Text to Contemporary Language for Improving Automatic Linguistic Annotation
TLDR
The CLIN27 shared task evaluates the effect of translating historical text to modern text with the goal of improving the quality of the output of contemporary natural language processing tools to historical text. Expand
  • 13
  • 1
  • PDF
...
1
2
3
...