• 1
• 2
• 3
• 4
• 5
• 6
• 7
1
Text-mining methods used 
for information extraction 
in plant scientific papers
1. Context
2CC-BY
Use-case : Regulatory Network in plant
How do genes regulate the development of 
my plant?
Information Extraction and Biology
3CC-BY
Lorem ipsum dolor sit 
amet, consectetur 
adipiscing elit. Quisque 
ante tellus, pulvinar 
vitae sollicitudin nec, 
posuere quis massa. 
Nulla justo augue, 
aliquam in euismod in, 
mollis id justo. Nullam 
massa massa, pharetra 
eget venenatis.
loremipsumdolorsitamet
consecteturadipiscingelit
quisqueantetelluspulvina
rvitaesollicitudinnecposu
erequismassanullajusto
auguealiquamineuismod
inmollisidjustonullamma
ssamassapharetraegetv
enenatis
lorem ipsum dolor sit 
amet, consectetur 
adipiscing elit quisque 
ante tellus, pulvinar 
vitae sollicitudin nec, 
posuere quis massa. 
nulla justo augue, 
aliquam in euismod in, 
mollis id justo nullam 
massa massa, pharetra 
eget venenatis.
A sequence of characters?
What is a text?
A sequence 
of words?
Words and 
sentences
4CC-BY
Specify the 
question
Define model 
and annotation 
language
Annote 
text
Train and apply 
the methods of 
Information 
Extraction
Evaluate 
and validate 
the 
extracted 
knowledge
TDM Application Design Approach
5CC-BY
Multiple steps are needed to go from a text 
corpus to relevant extracted information 
(entities and relations) 
How to process the text?
6CC-BY
The first steps usually involve tools to 
detect sentences and words, depending, 
for example, on spaces, punctuation, etc.
This is a text segmentation.
How to process the text?