peleiden / dalukeLinks
A Danish-speaking language model with entity-aware self-attention
☆9Updated 3 years ago
Alternatives and similar repositories for daluke
Users that are interested in daluke are comparing it to the libraries listed below
Sorting:
- A collection of Danish Transformers☆30Updated 3 years ago
- Fine-tuning of transformers for Sentiment Analysis☆19Updated 4 years ago
- DaCy: The State of the Art Danish NLP pipeline using SpaCy☆97Updated 7 months ago
- DaNLP is a repository for Natural Language Processing resources for the Danish Language.☆206Updated 6 months ago
- Ælæctra was created as part of a Cognitive Science bachelor thesis, in the attempt to enhance the Danish NLP community with a more effici…☆28Updated 2 years ago
- Pre-trained Nordic models for BERT☆174Updated 3 years ago
- This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with enti…☆244Updated 2 years ago
- Augmenty is an augmentation library based on spaCy for augmenting texts.☆156Updated last year
- Active Learning for Text Classification in Python☆621Updated 2 weeks ago
- The Danish Gigaword project☆16Updated 4 years ago
- Framework for fine-tuning pretrained transformers for Named-Entity Recognition (NER) tasks☆159Updated 2 years ago
- All the goto functions you need to handle NLP use-cases, integrated in NLPretext☆140Updated 4 months ago
- The robust European language model benchmark.☆114Updated this week
- A Python library for calculating a large variety of metrics from text☆343Updated 7 months ago
- SpanMarker for Named Entity Recognition☆446Updated 7 months ago
- just a bunch of useful embeddings for scikit-learn pipelines☆503Updated 4 months ago
- This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-s…☆218Updated 6 months ago
- spaCy-wrap is a wrapper library for spaCy for including fine-tuned transformers from Huggingface in your spaCy pipeline allowing you to i…☆46Updated last year
- skweak: A software toolkit for weak supervision applied to NLP tasks☆926Updated 11 months ago
- Set of vectorizers that extract keyphrases with part-of-speech patterns from a collection of text documents and convert them into a docum…☆265Updated 9 months ago
- Doubt your data, find bad labels.☆515Updated last year
- Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13☆183Updated 3 weeks ago
- Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: …☆337Updated 2 years ago
- A Scandinavian Benchmark for sentence embeddings☆40Updated 2 months ago
- The website for Danish Foundation Models, a project for training foundational Danish language model.☆74Updated this week
- Zero and Few shot named entity & relationships recognition☆383Updated 3 months ago
- 🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy☆319Updated 3 months ago
- Toolkit to help understand "what lies" in word embeddings. Also benchmarking!☆472Updated 2 years ago
- Danish Data Science Community's guide to sustainable data science☆19Updated 2 years ago
- A python package for benchmarking interpretability techniques on Transformers.☆214Updated 10 months ago