Novel Event Detection and Classification for Historical Texts

Abstract

Event processing is an active area of research in the Natural Language Processing community, but resources and automatic systems developed so far have mainly addressed contemporary texts. However, the recognition and elaboration of events is a crucial step when dealing with historical texts Particularly in the current era of massive digitization of historical sources: Research in this domain can lead to the development of methodologies and tools that can assist historians in enhancing their work, while having an impact also on the field of Natural Language Processing. Our work aims at shedding light on the complex concept of events when dealing with historical texts. More specifically, we introduce new annotation guidelines for event mentions and types, categorized into 22 classes. Then, we annotate a historical corpus accordingly, and compare two approaches for automatic event detection and classification following this novel scheme. We believe that this work can foster research in a field of inquiry as yet underestimated in the area of Temporal Information Processing. To this end, we release new annotation guidelines, a corpus, and new models for automatic annotation.

Assessing the impact of OCR noise on multilingual event detection over digitised documents

“…An important work presented an effort to gather requirements from domain experts about the linguistic annotation of events in the historical domain [61]. This research suggested that the development of annotation guidelines for the analysis of texts in a specific domain must be carried out jointly with experts.…”

“…collections of digitised and/or historical documents [61]. Second, they can be utilised to estimate the impact of the OCR process on this task and to reduce the human expertise and manual labor-intensive work for handvalidating transcribed documents.…”

Detecting Scenes in Fiction: A new Segmentation Task

“…Another way of modeling plot is to detect individual events in a text and then combining those to larger units and finally to a representation of the plot. There have been advances on the detection of events (Sprugnoli and Tonelli, 2019;Sims et al, 2019;Aldawsari and Finlayson, 2019) in texts. However, the definition of an event is unclear, with large possible differences in the level of granularity, making it an unstable starting point for analyzing plot.…”

Named Entity Recognition and Classification on Historical Documents: A Survey

“…As to traditional word embeddings, we could inventory two main resources. Sprugnoli et al [179] have released a collection of pre-trained word and sub-word English embeddings learned from a subset of the Corpus of Historical American English [40], considering 37k texts published between 1860 and 1939 amounting to about 198 million words. These embeddings of 300 dimensions are available according to three types of word representations: embeddings based on linear bag-of-words contexts (GloVe [143]), on dependency parse-trees (Levy et al [115]), and on bag of character n-grams (fastText [21]).…”