Language is often regarded as the hallmark of human intelligence. Developing systems that
can understand human language is thus one of the main obstacles on the quest towards …

Accurately detecting hate speech using supervised classification is dependent on data that
is annotated by humans. Attaining high agreement amongst annotators though is difficult …

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 combine multi-task learning and semi-supervised learning by inducing a joint
embedding space between disparate label spaces and learning transfer functions between …

Despite the ubiquity of mobile and wearable text messaging applications, the problem of
keyboard text decoding is not tackled sufficiently in the light of the enormous success of the …

Understanding historical events is necessary for the study of contemporary society, culture,
and politics. In this work, we focus on the event extraction task (EE) to detect event trigger …

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 …

Acquiring a single sentiment score dependent on all the reviews will benefit the buyers and
sellers in making the decision more accurately. The raw format of user-generated content …

This work describes the UoE-LMU submission for the CoNLL-SIGMORPHON 2017 Shared
Task on Universal Morphological Reinflection, Subtask 1: given a lemma and target …

In this paper, we apply different NMT models to the problem of historical spelling
normalization for five languages: English, German, Hungarian, Icelandic, and Swedish. The …