I had a lot of fun implementing a SPARQL editor for DanNet. During this process I also wrote a ton of new documentation, including a SPARQL tutorial that uses the new editor for its interactive examples.
The idea is, of course, to make the Danish WordNet more broadly accessible. Previously, you would have had to spin up your own RDF triplestore to query DanNet using SPARQL.
Весь такой перцептивный. Сенсорная атмосфера в прозе. Пример анализа художественного текста на Python
Анализ глаголов восприятия в прозе Паустовского с помощью Python: подход цифрового гуманитария для NLP-разработчиков.
https://habr.com/ru/articles/977210/
#проза #поэзия #писатель #python #pymorphy #tokenizer #spacy #wordnet
Константина Паустовского называют одним из писателей, проза которого "звучит" или "светится". Частное эмоциональное впечатление от чтения таких текстов – радостное и возвышенное. Иные поклонники...
Bheil fhios agaibh gur e #Wordnet air #Gàidhlig?
Chan eil fhios agam dè nì mi leis an fhios.
Ceangal ri The Unified Scottish Gaelic Wordnet http://ukc.disi.unitn.it/index.php/gaelic/
The Multilingual Sign Language Wordnet is the first publicly available wordnet resource for sign languages. It is a growing multilingual resource providing data for eight sign languages to...
Check out this poster I made for an upcoming conference. First time doing something like this—even had to design a logo—but I thought it turned out well.
Today, I spent some time sketching out a logo for DanNet (the Danish WordNet).
I need to make a poster for an upcoming NLP conference presenting my work on DanNet. The text of the poster was easy enough to write and I guess the illustrations will be mostly screenshots from https://wordnet.dk/dannet, but I needed to produce a new logo too, so I came up with this design which sort of resembles a hyponymy relationship, stylised as a basic directed graph.
I'm writing a paper with some colleagues where the idea is to construct a test dataset for #LLMs (such as those provided through #ChatGPT ) that specifically tests their knowledge of #Danish.
We are generating many of the tests from data found in the Danish #WordNet (#DanNet) which I maintain.
I am writing #SPARQL queries to get the data out. It's honestly turning into a test of DanNet itself, since the strength of the various (underspecified) RDF predicates can vary quite a bit.
Simon Gray
Habr
Kingsley Uyi Idehen
Mòrag
Marc Schulder
Petra Steiner