Mariona Coll Ardanuy, Federico Nanni, Kaspar Beelen, Kasra Hosseini, Ruth Ahnert, Jon Lawrence, Katherine McDonough, Giorgia Tolfo, Daniel CS Wilson, Barbara McGillivray. Proceedings of the 28th International Conference on Computational Linguistics. 2020.

A growing volume of heritage data is being digitized and made available as text via optical character recognition (OCR). Scholars and libraries are increasingly using OCR-generated text for retrieval and analysis. However, the process of creating text through OCR introduces varying degrees of error to the text. The impact of these errors on natural language processing (NLP) tasks has only been partially studied. We perform a series of extrinsic assessment tasks — sentence segmentation, named entity recognition, dependency parsing, information retrieval, topic modelling and neural language model fine-tuning — using popular, out-of-the-box tools in order to quantify the impact of OCR quality on these tasks. We find a consistent impact resulting from OCR errors on our downstream tasks with some tasks more irredeemably harmed by OCR errors. Based on these results, we offer some preliminary guidelines for working with text produced through OCR.

The practices of digital humanists are evolving, highly diversified and experimental. There is also a lack of agreement about whether or not digital humanists should have data and programming skills. Thus, their underlying needs for higher levels of flexibility and transparency may be contradicted by their explicit requests for user-friendly graphic user interfaces (GUIs), creating challenges for designing information systems in the digital humanities. This paper describes the experience of designing the Media Suite, which provides access to important Dutch audiovisual collections and is part of the Dutch infrastructure for digital humanities. We outline a solution to the conflicting needs of scholars, by combining a semi-traditional GUI with Jupyter Notebooks. This solution tackles the needs of both novice and advanced users in digital research methods in the humanities. This demonstration paper explains how the Media Suite and the Jupyter notebooks work together, and elaborates on the rationale behind the design choices. We also outline the implications this hybrid and extensible approach has for interface design for the information science and scholarly community.

Recently, researchers started to pay attention to the detection of temporal shifts in the meaning of words. However, most (if not all) of these approaches restricted their efforts to uncovering change over time, thus neglecting other valuable dimensions such as social or political variability. We propose an approach for detecting semantic shifts between different viewpoints---broadly defined as a set of texts that share a specific metadata feature, which can be a time-period, but also a social entity such as a political party. For each viewpoint, we learn a semantic space in which each word is represented as a low dimensional neural embedded vector. The challenge is to compare the meaning of a word in one space to its meaning in another space and measure the size of the semantic shifts. We compare the effectiveness of a measure based on optimal transformations between the two spaces with a measure based on the similarity of the neighbors of the word in the respective spaces. Our experiments demonstrate that the combination of these two performs best. We show that the semantic shifts not only occur over time but also along different viewpoints in a short period of time. For evaluation, we demonstrate how this approach captures meaningful semantic shifts and can help improve other tasks such as the contrastive viewpoint summarization and ideology detection (measured as classification accuracy) in political texts. We also show that the two laws of semantic change which were empirically shown to hold for temporal shifts also hold for shifts across viewpoints. These laws state that frequent words are less likely to shift meaning while words with many senses are more likely to do so.

This paper sets out to detect controversial news reports using online discussions as a source of information. We define controversy as a public discussion that divides society and demonstrate that a content and stylometric analysis of these debates yields useful signals for extracting disputed news items. Moreover, we argue that a debate-based approach could produce more generic models, since the discussion architectures we exploit to measure controversy occur on many different platforms.