Event Detection and Semantic Storytelling: Generating a Travelogue from a large Collection of Personal Letters

Abstract

We present an approach at identifying a specific class of events, movement action events (MAEs), in ca. 2,800 personal letters exchanged by the German architect Erich Mendelsohn and his wife, Luise. A backend system uses these and other semantic analysis results as input for an authoring environment that curators can use to produce new pieces of content. The human expert will receive recommendations from the system with the goal of putting together a travelogue, i. e., a description of the trips and journeys undertaken by the couple. We describe the components and also apply the system to news data.

Fine-Grained Named Entity Recognition in Legal Documents

“…Most NER solutions operate in the general or news domain, which makes them not completely suitable for the analysis of legal documents, because they are unable to detect domain-specific entities. The goal is to make knowledge workers, who process and make use of these documents, more efficient and more effective in their day to day work, this also includes the analysis of domain-specific NEs, see [5,31] for related approaches in the area of content curation technologies.…”

Curation Technologies for Cultural Heritage Archives

“…), which could be exploited further. An example of this, exploiting geographical co-ordinates is described in [27]. We plan to include similar functionality in later stages of the system.…”

“…This conversion of, for example, physical archives, into machine-readable formats is an important first step towards making sure the information is retained for future generations. The subsequent step, semi or maybe even fully automatically making sense of large volumes of content to enable humans quickly to grasp what is contained on a rather high level, and providing entry points for a more detailed exploration, i. e., the aggregation, sorting and re-arranging of both new and digitised information is what we perceive to be at the core of digital curation technologies [4,19,[25][26][27]. In this contribution we focus on importing, analysing and curating a cultural heritage archive in the form of a very large collection of PDF documents.…”

Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism

“…The cross-lingual detection of events encompasses a pipeline that ends up with a list of annotated events in every document (Rehm et al, 2017b).…”