We present our ongoing work on language technology-based e-science in the humanities, with a focus on text-based research in the historical sciences. Currently, we are working on the adaptation and integration of lexical resources representing different historical stages of Swedish into a lexical and morphological toolbox that will allow us to develop semantically oriented text search applicati...

Humanities scholars increasingly rely on digital archives for their research instead of time-consuming visits to physical archives. This shift in research method has the hidden cost of working with digitally processed historical documents: how much trust can a scholar place in noisy representations of source texts? In a series of interviews with historians about their use of digital archives, w...

This paper examines the effects of strategic alliances on non-financial firms’ bank loan financing. We construct several measures to capture firms’ alliance activities using the frequency of alliance activities, the prominence of the alliance partner and the relative networking position in the overall alliance network. We find that firms with active alliance involvement experience a lower cost ...

This paper proposes a novel method for document enhancement. The method is based on the combination of two state-of-the-art filters through the construction of a mask. The mask is applied to a TV (Total Variation) regularized image where background noise has been reduced. The masked image is then filtered by NLmeans (Non Local Means) which reduces the noise in the text areas located by the mask...

We present richer typesetting models that extend the unsupervised historical document recognition system of BergKirkpatrick et al. (2013). The first model breaks the independence assumption between vertical offsets of neighboring glyphs and, in experiments, substantially decreases transcription error rates. The second model simultaneously learns multiple font styles and, as a result, is able to...

This paper explores a method for creating large-scale urban 3D models using Historical GIS data. The method is capable of automatically generating realistic VR models based on GIS data at a low cost. 3D models of houses are created from polygon data, fences from line data, and pedestrians and trees from point data. The method is applied to the Virtual Kyoto Project in which the landscape of the...