Automatic annotation of incomplete and scattered bibliographical references in Digital Humanities papers

Automatic annotation of incomplete and scattered bibliographical references in Digital Humanities papers

The reviewed article presents the project BILBO and illustrates the application of several appropriate machine-learning techniques to the constitution of proper reference corpora and the construction of efficient annotation models. In this way, solutions are proposed for the problem of extracting and processing useful information from bibliographic references in digital documentation whatever their bibliographic styles are. It proves the usefulness and high degree of accuracy of CRF techniques, which involve finding the most effective set of features (including three types of features: input, local and global features) of a given corpus of well-structured bibliographical data (with labels such as surname, forename or title). Moreover, this approach has not only been proven efficient when applied to such traditional, well-structured bibliographical data sets, but it also originally contributes to the processing of more complicated, less-structured references such as the ones contained in footnotes by applying SVM with new features for sequence classification.

[Click ‘Read more’ for the full post.]

Mining ethnicity: Discourse-driven topic modelling of immigrant discourses in the USA, 1898–1920

Mining ethnicity: Discourse-driven topic modelling of immigrant discourses in the USA, 1898–1920

Introduction: The article illustrates the application of a ‘discourse-driven topic modeling’ (DDTM) to the analysis of the corpus ChronicItaly comprising several newspapers in Italian language, appeared in the USA during the time of massive migration towards America between the end of the XIX century and the first two decades of the XX (1898-1920).

The method combines both Text Modelling (™) and the discourse-historical approach (DHA) in order to get a more comprehensive representation of the ethnocultural and linguistic identity of the Italian group of migrants in the historical American context in crucial periods of time like that immediately preceding the eruption and that of the unfolding of World War I.

Analyzing Documents with TF-IDF | Programming Historian

Analyzing Documents with TF-IDF | Programming Historian

Introduction: The indispensable Programming Historian comes with an introduction to Term Frequency – Inverse Document Frequency (tf-idf) provided by Matthew J. Lavin. The procedure, concerned with specificity of terms in a document, has its origins in information retrieval, but can be applied as an exploratory tool, finding textual similarity, or as a pre-processing tool for machine learning. It is therefore not only useful for textual scholars, but also for historians working with large collections of text.

Do humanists need BERT?

Do humanists need BERT?

Introduction: Ted Underwood tests a new language representation model called “Bidirectional Encoder Representations from Transformers” (BERT) and asks if humanists should use it. Due to its high degree of difficulty and its limited success (e.g. in questions of genre detection) he concludes, that this approach will be important in the future but it’s nothing to deal with for humanists at the moment. An important caveat worth reading.