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.

Recognizing toponyms and resolving them to their real-world referents is required to provide advanced semantic access to textual data. This process is often hindered by the high degree of variation in toponyms. Candidate selection is the task of identifying the potential entities that can be referred to by a previously recognized toponym. While it has traditionally received little attention, candidate selection has a significant impact on downstream tasks (i.e. entity resolution), especially in noisy or non-standard text. In this paper, we introduce a deep learning method for candidate selection through toponym matching, using state-of-the-art neural network architectures. We perform an intrinsic toponym matching evaluation based on several datasets, which cover various challenging scenarios (cross-lingual and regional variations, as well as OCR errors) and assess its performance in the context of geographical candidate selection in English and Spanish.

Geographic text analysis (GTA) research in the digital humanities has focused on projects analyzing modern English-language corpora. These projects depend on temporally specific lexicons and gazetteers that enable place name identification and georesolution. Scholars working on the early modern period (1400–1800) lack temporally appropriate geoparsers and gazetteers and have been reliant on general purpose linked open data services like Geonames. These anachronistic resources introduce significant information retrieval and ethical challenges for early modernists. Using the geography entries of the canonical eighteenth-century Encyclopédie, we evaluate rule-based named entity recognition (NER) systems to pinpoint areas where they would benefit from adjustments for processing historical corpora. As we demonstrate, annotating nested and extended place information is one way to improve early modern GTA. Working with Enlightenment sources also motivates a critique of the landscape of digital geospatial data.

Effectively exploring and browsing document collections is a fundamental problem in visualization. Traditionally, document visualization is based on a data model that represents each document as the set of its comprised words, effectively characterizing what the document is. In this paper we take an alternative perspective: motivated by the manner in which users search documents in the research process, we aim to visualize documents via their usage, or how documents tend to be used. We present a new visualization scheme - cite2vec - that allows the user to dynamically explore and browse documents via how other documents use them, information that we capture through citation contexts in a document collection. Starting from a usage-oriented word-document 2D projection, the user can dynamically steer document projections by prescribing semantic concepts, both in the form of phrase/document compositions and document:phrase analogies, enabling the exploration and comparison of documents by their use. The user interactions are enabled by a joint representation of words and documents in a common high-dimensional embedding space where user-specified concepts correspond to linear operations of word and document vectors. Our case studies, centered around a large document corpus of computer vision research papers, highlight the potential for usage-based document visualization.