Discover @boudinfl Open Source projects

Florian Boudin (@boudinfl)

boudinfl

Stars
1,760
Global Rank 17,534 (Top 0.7 %)
Followers 148
Following 2
Registered about 13 years ago
Most used languages

Python
47.4 %

Shell
15.8 %

TeX
15.8 %

Jupyter Notebook
10.5 %

HTML
5.3 %

JavaScript
5.3 %
Location 🇫🇷 France
Country Total Rank 531
Country Ranking

TeX
73

Python
78

Shell
139

Jupyter Notebook
2,067

JavaScript
3,841

HTML
6,415

pke

Python Keyphrase Extraction module

ake-datasets

Large, curated set of benchmark datasets for evaluating automatic keyphrase extraction algorithms.

takahe

takahe is a multi-sentence compression module

sume

Sume is an implementation of the concept-based ILP model for summarization.

centrality_measures_ijcnlp13

Centrality Measures for Graph-Based Keyphrase Extraction

taln-archives

TALN Archives is a digital archive of French research articles in Natural Language Processing

kea

A tokenizer for French

ir-using-kg

Keyphrase Generation for Scientific Document Retrieval

acm-cr

ACM-CR: A Manually Annotated Test Collection for Citation Recommendation

hulth-2003-pre

Preprocessed Inspec keyphrase extraction benchmark dataset

duc-2001-pre

Preprocessed DUC 2001 keyphrase extraction benchmark dataset

semeval-2010-pre

Preprocessed SemEval-2010 benchmark dataset for keyphrase extraction

marujo-2012-pre

Preprocessed Marujo keyphrase extraction benchmark dataset

redefining-absent-keyphrases

Code and dataset for the paper "Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness"

krapivin-2009-pre

Preprocessed Krapivin keyphrase extraction benchmark dataset

lina-msc

LINA-msc is a dataset for evaluating Multi-sentence Compression in French.

kepy

kepy is a keyphrase extraction module in Python

cross-language_IR

Un cours de deux heures sur la recherche d'information cross-lingue

wikinews-2013-pre

Preprocessed Wikinews Keyphrase benchmark dataset

boudinfl.github.io

CLIREC

CLinical Information Retrieval Evaluation Collection

Jupyter Notebook

pke-benchmarking

Jupyter Notebook