TurkuNLP/RAG-web-app

Stars
3
Rank 3,963,521 (Top 79 %)
Language
HTML
Created 7 months ago
Updated about 2 months ago

TurkuNLP/RAG-web-app

TurkuNLP

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Turku-neural-parser-pipeline

A neural parsing pipeline for segmentation, morphological tagging, dependency parsing and lemmatization with pre-trained models for more than 50 languages. Top ranker in the CoNLL-18 Shared Task.

FinBERT

BERT model trained from scratch on Finnish

Finnish-dep-parser

The Finnish dependency parsing pipeline being developed by the Turku NLP group. Documentation:

wikibert

BERT models for many languages created from Wikipedia texts

Text_Mining_Course

Stuff for the Text Mining course

Jupyter Notebook

ocr-correction

Post-processing OCR errors with seq2seq models

finngen-tools

Tools for training causal language models for Finnish

Deep_Learning_in_LangTech_course

Materials for the University of Turku course TKO_8965 Deep Learning in Human Language Technology (previously named TKO_2101 Natural Language Processing)

Jupyter Notebook

bert-eval

turku-ner-corpus

Open broad-coverage corpus for Finnish named entity recognition.

turku-one

Turku OntoNotes Entities Corpus (TurkuONE)

pubmed_parses

Syntactic parses and named entity recognition for PubMed abstracts and PubMed Central full documents

finnish-generative-model-eval

Evaluation of Finnish generative models

class-explainer

IR_Course

Stuff for the upcoming IR course 2017

Jupyter Notebook

Finnish_PropBank

Finnish Proposition Bank

intro-to-nlp

Introduction to Natural Language Processing

Jupyter Notebook

register-labeling

Turku-paraphrase-corpus

biBERT

Finnish English bilingual BERT models

BINF_Programming

Stuff for the BINF programming course (@fginter)

Jupyter Notebook

ATP_kurssi

Jupyter Notebook

multilingual-register-labeling

Multilingual, multilabel modeling of registers

CAFA3

University of Turku CAFA3 project

conll17-system

Instructions for TurkuNLP system in CoNLL 2017 Shared Task on Multilingual Parsing from Raw Text to Universal Dependencies.

WAC-XII

Data presented in the paper "From Web Crawl to Clean Register-Annotated Corpora"

textual-data-analysis-course

Jupyter Notebook

DIKI1002-Working-with-Text-in-Python

Jupyter Notebook

FinCORE

Finnish Corpus of Online REgisters

BioCreativeVI_CHEMPROT_RE

Deep learning-based systems for biomedical relation extraction: recognizing the statements of relations between chemical compounds/drugs and genes/proteins from biomedical literature. The code is developed for our participation in the BioCreative VI Task 5 (CHEMPROT) challenge. Contact: [email protected]

BioCreativeVI_BioID_assignment

Corpus-linguistics

Code and data for the examples and use cases described in the article "Määrällinen korpuslingvistiikka" to be published in the book "Kielentutkimuksen metodologian käsikirja" in Finnish.

korona-tweets

stuff for our korona-tweets

ocr_errors_simulator

Functions and codes used to determine probabilities on OCR errors and simulate them

registerlabeling

Cell-line-recognition

Cell line names recognition and normalization

Digi_menetelmat

Johdatus digitaalisiin ihmistieteisiin -kurssin työpaja "Digitaaliset ihmistieteet kielentutkimuksessa: tekstinlouhinta"

Multilingual-register-corpora

French Corpus of Online REgisters (FreCORE) and Swedish Corpus of Online REgisters (SweCORE)

BHE

End-to-end System for Bacteria Habitat Extraction: Named-entity recognition (NER), named-entity normalization, relation extraction. email: [email protected]

dolly-fi

Finnish version of databricks-dolly-15k instruction dataset

sentiment-target-corpus

Targeted sentiment corpus

dep_search

deepfin-tools

SRNNMT

Sentence representation for translation finding

CORE-corpus

FinCORE_full

oasst-fi

Open Assistant dataset translated to Finnish

DigiHum16

Random course notes for the DigiHum16 course

Jupyter Notebook

wikipedia-toxicity-data-fi

toxicity-classifier

Repository for all things related to classifying whether a text is toxic or not using data from https://github.com/TurkuNLP/wikipedia-toxicity-data-fi

PB_solr

Work towards indexing the Finnish Parsebank in SOLR

TDT_editor

The tree editor used to annotate the Turku Dependency Treebank. Vintage code, but putting it online in case someone finds it in any way useful.

pytorch-registerlabeling

Jupyter Notebook