• Stars
    star
    12
  • Rank 1,597,372 (Top 32 %)
  • Language
    Python
  • License
    GNU General Publi...
  • Created over 8 years ago
  • Updated over 8 years ago

Reviews

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

Repository Details

More Repositories

1

edgar-crawler

The only open-source toolkit that can download EDGAR financial reports and extract textual data from specific item sections into nice and clean JSON files.
Python
257
star
2

greek-bert

A Greek edition of BERT pre-trained language model
Python
140
star
3

deep-relevance-ranking

Deep Relevance Ranking Using Enhanced Document-Query Interactions
Python
113
star
4

bio_image_caption

Biomedical Image Captioning
Python
52
star
5

finer

FiNER: Financial Numeric Entity Recognition for XBRL Tagging
Python
51
star
6

gr-nlp-toolkit

The state-of-the-art NLP toolkit for Modern Greek.
Python
48
star
7

multi-eurlex

MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer
Python
32
star
8

aueb-absa

Python
25
star
9

SumQE

SUM-QE, a BERT-based Summary Quality Estimation Model
Python
21
star
10

bioCaption

Diagnostic Captioning
Python
16
star
11

BioIR

Using Centroids of Word Embeddings and Word Mover's Distance for Biomedical Document Retrieval in Question Answering.
Python
15
star
12

imageclef2024

Participation of the AUEB NLP Group in the 8th edition of the ImageCLEFmedical Caption evaluation campaign
Python
8
star
13

dmmcs

Distance from Median Maximum Cosine Similarity
Python
8
star
14

aueb-bioasq6

AUEB at BioASQ 6: Document and Snippet Retrieval
Python
7
star
15

aueb-bioasq7

AUEB at BioASQ 7: Document and Snippet Retrieval
C
6
star
16

mcm-civil-procedure

Multiple Choice Mutation (MCM) is a technique for generating good quality domain-specific synthetic data with an LLM.
Jupyter Notebook
1
star
17

nlp-optimizers

Python
1
star