Named Entity Recognition and Classification on Historical Documents: A Survey

Abstract

After decades of massive digitisation, an unprecedented amount of historical documents is available in digital format, along with their machine-readable texts. While this represents a major step forward with respect to preservation and accessibility, it also opens up new opportunities in terms of content mining and the next fundamental challenge is to develop appropriate technologies to efficiently search, retrieve and explore information from this 'big data of the past'. Among semantic indexing opportunities, the recognition and classification of named entities are in great demand among humanities scholars. Yet, named entity recognition (NER) systems are heavily challenged with diverse, historical and noisy inputs. In this survey, we present the array of challenges posed by historical documents to NER, inventory existing resources, describe the main approaches deployed so far, and identify key priorities for future developments.

Genealogical Data Mining from Historical Archives: The Case of the Jewish Community in Pisa

“…Historical and ancient texts pose many challenges for entity extraction, such as spelling variation, language change, and lack of large corpora. The main techniques to extract entities from historical texts include temporal entity extraction, event extraction, and named entity recognition (NER) [25,26]. In many cases, entity extraction is performed manually [27].…”

Historical-Domain Pre-trained Language Model for Historical Extractive Text Summarization

“…Therefore, we will review research on historical NLP applications and extractive supervised text summarization methods. For a detailed review, readers may refer to [18], [19] and [20], [21] surveys, respectively.…”

“…Existing NLP studies on historical documents primarily focus on tasks such as spelling normalization [18], [23], machine translation [24], and sequence labelling, including part-of-speech tagging [25] and named entity recognition [19], [26]. Recently, the success of deep neural networks has introduced new applications in this domain, including sentiment analysis [27], information retrieval [28], event extraction [29], [30], and text classification [31].…”

Introducing the HIPE 2022 Shared Task: Named Entity Recognition and Linking in Multilingual Historical Documents

“…Yet, the recognition, classification and disambiguation of NEs in historical texts are not straightforward, and performances are not on par with what is usually observed on contemporary well-edited English news material [3]. In particular, NE processing on historical documents faces the challenges of domain heterogeneity, input noisiness, dynamics of language, and lack of resources [6]. Although some of these issues have already been tackled in isolation in other contexts (with e.g., user-generated text), what makes the task particularly difficult is their simultaneous combination and their magnitude: texts are severely noisy, and domains and time periods are far apart.…”