Sarah Schulz

Multimodular Text Normalization of Dutch User-Generated Content

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 language processing (NLP) tools, as these are typically trained on standard language material. We propose a text normalization approach to tackle this problem. More specifically, we investigate the usefulness of a multimodular approach to account for the diversity of normalization issues encountered in user-generated content (UGC). We consider three different types of UGC written in Dutch (SNS, SMS, and tweets) and provide a detailed analysis of the performance of the different modules and the overall system. We also apply an extrinsic evaluation by evaluating the performance of a part-of-speech tagger, lemmatizer, and named-entity recognizer before and after normalization.

A Rho signaling network links microtubules to PKD controlled carrier transport to focal adhesions

Protein kinase D (PKD) is a family of serine/threonine kinases that is required for the structural integrity and function of the Golgi complex. Despite its importance in the regulation of Golgi function, the molecular mechanisms regulating PKD activity are still incompletely understood. Using the genetically encoded PKD activity reporter G-PKDrep we now uncover a Rho signaling network comprising GEF-H1, the RhoGAP DLC3, and the Rho effector PLCε that regulate the activation of PKD at trans-Golgi membranes. We further show that this molecular network coordinates the formation of TGN-derived Rab6-positive transport carriers delivering cargo for localized exocytosis at focal adhesions.

Code-Switching Ubique Est - Language Identification and Part-of-Speech Tagging for Historical Mixed Text

In this paper, we describe the development of a language identification system and a part-of-speech tagger for Latin-Middle English mixed text. To this end, we annotate data with language IDs and Universal POS tags (Petrov et al., 2012). As a classifier, we train a conditional random field classifier for both sub-tasks, including features generated by the TreeTagger models of both languages. The focus lies on both a general and a task-specific evaluation. Moreover, we describe our effort concerning beyond proof-of-concept implementation of tools and towards a more task-oriented approach, showing how to apply our techniques in the context of Humanities research.

OVERGENERALIZATION OF VERBS - THE CHANGE OF THE GERMAN VERB SYSTEM

In this paper we want to show, that the change of the German verb system from Middle High German to New High German can be simulated and explained by an adoption of the Iterated Learning Model. We claim, that the change of the German verb system is due to the frequency of usage and the process of overgeneralization. This is the first application of an Iterated Learning Model simulating the change of “real” German language, so we can also prove the quality of the Iterated Learning Model as an explanatory model for language change.