Walter Daelemans

Data integration of structured and unstructured sources for assigning clinical codes to patient stays

2015 · Journal of the American Medical Informatics Association

OBJECTIVE: Enormous amounts of healthcare data are becoming increasingly accessible through the large-scale adoption of electronic health records. In this work, structured and unstructured (textual) data are combined to assign clinical diagnostic and procedural codes …

Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution

2017

Recent applications of neural language models have led to an increased interest in the automatic generation of natural language. However impressive, the evaluation of neurally generated text has so far remained rather informal and anecdotal. …

Character-Level Transformer-Based Neural Machine Translation

2020

Neural machine translation (NMT) is nowadays commonly applied at the subword level, using byte-pair encoding. A promising alternative approach focuses on character-level translation, which simplifies processing pipelines in NMT considerably. This approach, however, must consider …

Multimodular Text Normalization of Dutch User-Generated Content

2016 · ACM Transactions on Intelligent Systems and Technology

As social media constitutes a valuable source for data analysis for a wide range of applications, the need for handling such data arises. However, the nonstandard language used on social media poses problems for natural …