Multilingual Event Extraction from Historical Newspaper Adverts

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 10304–10325 July 9-14, 2023 ©2023 Association for Computational Linguistics Multilingual Event Extraction from Historical Newspaper Adverts WARNING: This paper shows dataset samples which are racist in nature Nadav Borenstein University of Copenhagen nadav.borenstein@di.ku.dk Natália da Silva Perez Erasmus University Rotterdam dasilvaperez@eshcc.eur.nl Isabelle Augenstein University of Copenhagen augenstein@di.ku.dk Abstract NLP methods can aid historians in analyzing textual materials in greater volumes than manu- ally feasible. Developing such methods poses substantial challenges though. First, acquiring large, annotated historical datasets is difficult, as only domain experts can reliably label them. Second, most available off-the-shelf NLP mod- els are trained on modern language texts, ren- dering them significantly less effective when ap- plied to historical corpora. This is particularly problematic for less well studied tasks, and for languages other than English. This paper ad- dresses these challenges while focusing on the under-explored task of event extraction from a novel domain of historical texts. We introduce a new multilingual dataset in English, French, and Dutch composed of newspaper ads from the early modern colonial period reporting on enslaved people who liberated themselves from enslavement. We find that: 1) even with scarce annotated data, it is possible to achieve surpris- ingly good results by formulating the problem as an extractive QA task and leveraging exist- ing datasets and models for modern languages; and 2) cross-lingual low-resource learning for historical languages is highly challenging, and machine translation of the historical datasets to the considered target languages is, in practice, often the best-performing solution. 1 Introduction Analyzing large corpora of historical documents can provide invaluable insights on past events in multiple resolutions, from the life of an individual to processes on a global scale (Borenstein et al., 2023; Laite, 2020; Gerritsen, 2012). While histo- rians traditionally work closely with the texts they study, automating parts of the analysis using NLP tools can help speed up the research process and facilitate the extraction of historical evidence from large corpora, allowing historians to focus on inter- pretation. However, building NLP models for historical texts poses a substantial challenge. First, acquir- ing large, annotated historical datasets is difficult (Hämäläinen et al., 2021; Bollmann and Søgaard, 2016), as only domain experts can reliably label them. This renders the default fully-supervised learning setting less feasible for historical corpora. Compounding this, most off-the-shelf NLP models were trained on modern language texts and display significantly weaker performance for historical doc- uments (Manjavacas and Fonteyn, 2022; Baptiste et al., 2021; Hardmeier, 2016), which usually suf- fer from a high rate of OCR errors and are written in a substantially different language. This is partic- ularly challenging for less well-studied tasks or for non-English languages. One of these under-explored tasks is event extrac- tion from historical texts (Sprugnoli and Tonelli, 2019; Lai et al., 2021), which can aid in retriev- ing information about complex events from vast amounts of texts. Here, we research extraction of events from adverts in colonial …

Content truncated to 500 words