LoGaRT and RISE: Two multilingual tools from the Max Planck Institute for the History of Science

LoGaRT and RISE: Two multilingual tools from the Max Planck Institute for the History of Science

Introduction: This post introduces two tools developed by the Max Planck Institute for the History of Science, LoGaRT and RISE with a focus on Asia and Eurasia. […]The concept of LoGaRT – treating local gazetteers as “databases” by themselves – is an innovative and pertinent way to articulate the essence of the platform: providing opportunities for multi-level analysis from the close reading of the sources (using, for example, the carousel mode) to the large-scale, “bird’s eye view” of the materials across geographical and temporal boundaries. Local gazetteers are predominantly textual sources – this characteristic of the collection is reflected in the capabilities of LoGaRT as well, since some of its key capabilities include data search (using Chinese characters), collection and analysis, as well as tagging and dataset comparison. That said, LoGaRT also offers integrated visualization tools and supports the expansion of the collection and tagging features to the images used in a number of gazetteers. The opportunity to smoothly intertwine these visual and textual collections with Chinese historical maps (see CHMap) is an added, and much welcome, advantage of the tool, which helps to develop sophisticated and multifaceted analyses.
[Click ‘Read more’ for the full post!]

BERT for Humanists: a deep learning language model  meets DH

BERT for Humanists: a deep learning language model meets DH

Introduction: Awarded as Best Long Paper at the 2019 NACCL (North American Chapter of the Association for Computational Linguistics) Conference, the contribution by Jacob Devlin et al. provides an illustration of “BERT: Pre-training of Deep Biredictional Transformers for Language Understanding” (https://aclanthology.org/N19-1423/).

As highlighted by the authors in the abstract, BERT is a “new language representation model” and, in the past few years, it has become widespread in various NLP applications; for example, a project exploiting it is CamemBERT (https://camembert-model.fr/), regarding French. 

In June 2021, a workshop organized by David Mimno, Melanie Walsh and Maria Antoniak (https://melaniewalsh.github.io/BERT-for-Humanists/workshop/) pointed out how to use BERT in projects related to digital humanities, in order to deal with word similarity and classification classification while relying on Phyton-based HuggingFace transformers library. (https://melaniewalsh.github.io/BERT-for-Humanists/tutorials/ ). A further advantage of this training resource is that it has been written with sensitivity towards the target audience in mind:  in a way that it provides a gentle introduction to complexities of language models to scholars with education and background other than Computer Science.

Along with the Tutorials, the same blog includes Introductions about BERT in general and in its specific usage in a Google Colab notebook, as well as a constantly-updated bibliography and a glossary of the main terms (‘attention’, ‘Fine-Tune’, ‘GPU’, ‘Label’, ‘Task’, ‘Transformers’, ‘Token’, ‘Type’, ‘Vector’).

A World of Possibilities: a corpus-based approach to the diachrony of modality in Latin

A World of Possibilities: a corpus-based approach to the diachrony of modality in Latin

Introduction: Hosted at the University of Lausanne, “A world of possibilities. Modal pathways over an extra-long period of time: the diachrony in the Latin language” (WoPoss) is a project under development exploiting a corpus-based approach to the study and reconstruction of the diachrony of modality in Latin.
Following specific annotation guidelines applied to a set of various texts pertaining to the time span between 3rd century BCE and 7th century CE, the work team lead by Francesca Dell’Oro aims at analyzing the patterns of modality in the Latin language through a close consideration of lexical markers.

Pipelines for languages: not only Latin! The Italian NLP Tool (Tint)

Pipelines for languages: not only Latin! The Italian NLP Tool (Tint)

The StandforCore NLP wishes to represent a complete Java-based set of tools for various aspects of language analysis, from annotation to dependency parsing, from lemmatization
to coreference resolution. It thus provides a range of tools which
can be potentially applied to other languages apart from English.

Among the languages to which the StandfordCore NLP is mainly applied there is Italian, for which the Tint pipeline has been developed as described in the paper “Italy goes to Stanford: a collection of CoreNLP modules for Italian” by Alessio Palmero Apostolo and Giovanni Moretti.

On the Tint webpage the whole pipeline can be found and downloaded: it comprises tokenization and sentence splitting, morphological analysis and lemmatization, part-of-speech tagging, named-entity recognition and dependency parsing, including wrappers under construction. [Click ‘Read more’ for the whole post.]

Topic Modeling mit dem DARIAH Topics Explorer | forTEXT

Topic Modeling mit dem DARIAH Topics Explorer | forTEXT

Introduction: The first steps into working with digital methods of text analysis are often made with beginner-friendly tools. The DARIAH-DE TopicsExplorer opens up the world of topic modeling with an easy-to-understand GUI, numerous operating options and high-quality results. The team of forText of the University of Hamburg developed a tutorial (Lerneinheit) to guide users step by step from installing the software to the first results with a sample corpus. The tutorial also contains screenshots, videos, exercises and explanations. This follows the didactic concept of forText.

Transkribus & Magazines: Transkribus’ Transcription & Recognition Platform (TRP) as Social Machine…

Transkribus & Magazines: Transkribus’ Transcription & Recognition Platform (TRP) as Social Machine…

Introduction: This article proposes establishing a good collaboration between FactMiners and the Transkribus project that will help the Transkribus team to evolve the “sustainable virtuous” ecosystem they described as a Transcription & Recognition Platform — a Social Machine for Job Creation & Skill Development in the 21st Century!