Challenging America: Modeling language in longer time scales

Abstract

The aim of the paper is to apply, for historical texts, the methodology used commonly to solve various NLP tasks defined for contemporary data, i.e. pre-train and fine-tune large Transformer models. This paper introduces an ML challenge, named Challenging America (Chal-lAm), based on OCR-ed excerpts from historical newspapers collected from the Chronicling America portal. ChallAm provides a dataset of clippings, labeled with metadata on their origin, and paired with their textual contents retrieved by an OCR tool. Three, publicly available, ML tasks are defined in the challenge: to determine the article date, to detect the location of the issue, and to deduce a word in a text gap (cloze test). Strong baselines are provided for all three ChallAm tasks. In particular, we pretrained a RoBERTa model from scratch from the historical texts. We also discuss the issues of discrimination and hate-speech present in the historical American texts.

Temporal Image Caption Retrieval Competition – Description and Results

“…Several textual benchmarks concerning the date of text publication have been published in recent years. Challenging America [3] presents a set of three temporal tasks. Authors of [5] introduce a temporal question answering task and dataset, in which the query's answer depends on a year, e.g., Who is the current president of the USA?.…”

“…The final split ratio is illustrated in Table I. Precautions similar to those described in [3] have been taken to ensure that there is no detrimental overlap between the datasets.…”

“…The presented task is based on the projects: Chronicling America [2] and Challenging America [3]. Chronicling America is an open database of over 16 million pages of digitized historic American newspapers covering 274 years.…”

Multimodal Neural Networks in the Problem of Captioning Images in Newspapers

“…The competition dataset is based on the project "Challenging America" [16], which was initially created for three tasks. The first task, known as "RetroTemp", focused on temporal classification.…”

Temporal Language Modeling for Short Text Document Classification with Transformers

“…[18] trained an SVM model to predict the date of text as a classification problem and [11] use approach of neologism based approach. Very recently [15] released temporal NLP challenges based on a large corpus of historic texts but didn't include downstream tasks, such as classification. The corpus consists of texts covering over 100 years.…”