Tutorial on NE processing for Digital Humanities - DH Utrech 2019
-
Updated
Jul 18, 2019 - Jupyter Notebook
Tutorial on NE processing for Digital Humanities - DH Utrech 2019
🏮 OCR & transliteration pipeline for classical Sino-Vietnamese manuscripts — PaddleOCR + Right-to-Left layout analysis + 11,214-word Hán-Việt dictionary + S1∩S2 Levenshtein alignment. Digitizing "An Nam Nhất Thống Chí" (安南一統志) one character at a time.
This database compiles structured data from Chinese *leishu* (encyclopedic compendia), providing convenient access and support for researchers.
Generates structured summaries, timelines, and thematic insights from historical or cultural texts using pattern matching and language models.
Small Python wrapper class for the CAB webservice.
清代避讳定位器:用于在古籍 TXT、DOCX、EPUB 或者已经OCR的文本中定位清代避讳字词的研究工具。A research tool for locating Qing dynasty taboo-character evidence in Chinese classical texts.
A critical Digital Humanities project examining Montesquieu's De l'esprit des lois Book XIX through computational methods that expose the friction between contextual humanistic philosophy and digital infrastructure designed for other purposes.
A study on the historical authenticity of a text. The historical authenticity is evaluated by comparing the frequencies of unigrams, bigrams and trigrams of a given text to the frequencies of the ngrams of texts written in the period of +/- 5 years from the claimed date of the release of the given text and to the frequency of the ngrams of recen…
ChunQiuTR: Code and benchmark for time-keyed temporal retrieval in Classical Chinese annals
Automatic Machine Translation by rewriting archaic Italian into modern Italian with transformers, LLM prompting, and LLM-as-a-judge evaluation.
This R data package provides access to texts of Peace Books, reference reports prepared by the Historical Section of the British Foreign Office between 1918 and 1919 for use by the British Delegation at the Paris Peace Conference in 1919.
📜 Transform historical and thematic text into structured data with precision using this Python package, ensuring consistent results with pattern validation.
To associate your repository with the historical-texts topic, visit your repo's landing page and select "manage topics."