 |
Volumes
2025
(9 articles)
2024
(22 articles)
2023
(22 articles)
2022
(12 articles)
2021
(12 articles)
2020
(19 articles)
2019
(8 articles)
The volume also comprises papers published in special issues.
2018
(13 articles)
2017
(15 articles)
2016
(1 article)
2015
(3 articles)
2014
(6 articles)
CNLP4DH
(1 article)
Chinese natural language for digital humanities
Special Issue on Scientific and Technological Strategic Intelligence (2016)
(5 articles)
best papers on data mining and big data
Atelier Digit_Hum
(12 articles)
Special issue on Visualisations in Historical Linguistics
(8 articles)
Special issue conceived as a follow-up publication to the workshop on Visualisations in Historical Linguistics, organized as part of the ICEHL conference (27-31 August 2018), with additional papers resulting from an additional call for papers.
Special Issue on Collecting, Preserving, and Disseminating Endangered Cultural Heritage for New Understandings through Multilingual Approaches
(5 articles)
The existing reservoir of public domain translations of literary texts, once tracked and digitalized, provides a new wealth of linguistic resources to sustain and salvage endangered languages and help us map the global circulation and reception of texts.
HistoInformatics
(7 articles)
NLP4DH
(34 articles)
Towards robotic translation?
(17 articles)
The appearance on the web in 2017 of new translation services based on “deep learning” artificial intelligence algorithms such as DeepL and Google Translate corresponded to a new leap forward in machine translation. These recent systems, like the previous generation of statistical machine translation and factored machine translation, rely on large aligned corpora and produce results whose quality is in some cases comparable to some human translations. It follows that to produce added value, the translator must provide something extra compared to the machine. This added value may be inherent in fields where the use of machines is not in itself of much interest because of the essentially aesthetic dimension of translation: this is the case for the translation of certain literary genres. Although much academic translation research refers to this field, it represents only a small fraction of the existing professional translation activity. As the machine allows productivity gains of 150 to 200% (some translators reach outputs of 6,000 to 8,000 words per day), the post-editing technique is becoming increasingly important in the language industries, as confirmed in 2017 by the introduction of the ISO 18587 standard “Translation services — Post-editing of machine translation output — Requirements”. Post-editing poses a moral dilemma for translators: accepting that the machine, and not them, is the source of their own translation. Artificial intelligence is changing our professional activities and translation is one of the fields showing such changes. This issue brings together articles that do not aim to take stock, but rather to present reflections and practical experience not only from professional translators but also from academics specialising in teaching and/or researching translation. The rapid development of artificial intelligence is forcing not only professional translators but also translation courses to adapt. The approaches put into dialogue in this volume concern translation, but also natural langage processing, linguistics, translation studies and language teaching.
Historical Documents and automatic text recognition
(12 articles)
With this special issue of the Journal of Data Mining and Digital Humanities (JDMDH), we wish to bring together in one single volume several experiments, projects and reflections related to automatic text recognition on Historical documents. This special issue is the outcome of an event that took place at the Ecole Nationale des Chartes in Paris on June 23 and 24, 2022, which brought together scholars from various backgrounds to discuss the use of HTR and OCR in their researches. During these days, problems of engineering, machine learning or infrastructure were raised. Many technical subjects such as segmentation or the development of models linked to philological questions were discussed. The different speeches covered a large number of documents: manuscripts, archives, epigraphic materials, documents, sometimes in languages with their own specificities such as Hebrew, CHAM or ancient Greek from the 11th to the 20th century.