Prior work on controllable text generation usually assumes that the controlled attribute can
take on one of a small set of values known a priori. In this work, we propose a novel task …

There is no consensus on the state-of-the-art approach to historical text normalization. Many
techniques have been proposed, including rule-based methods, distance metrics, character …

We propose a generative model for a sentence that uses two latent variables, with one
intended to represent the syntax of the sentence and the other to represent its semantics. We …

Development sets are impractical to obtain for real low-resource languages, since using all
available data for training is often more effective. However, development sets are widely …

Question answering (QA) and Machine Reading Comprehension (MRC) tasks have
significantly advanced in recent years due to the rapid development of deep learning …

With the increasing availability of digitized resources of historical documents, interest in
effective natural language processing (NLP) for these documents is on the rise. However …

The digitisation of historical documents has provided historians with unprecedented
research opportunities. Yet, the conventional approach to analysing historical documents …

Using multiple treebanks to improve parsing performance has shown positive results.
However, to what extent similar, yet competing annotation decisions play in parser behavior …

Historical text normalization, the task of mapping historical word forms to their modern
counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; …

We investigate when is it beneficial to simultaneously learn representations for several
tasks, in low-resource settings. For this, we work with noisy user-generated texts in Algerian …