Summer School: Data Science for Document Analysis and Understanding

Inria Saclay, batiment Alan Turing	Data Science for Document Analysis and Understanding Part 2 INRIA (French Institute for Research in Computer Science and Automation) (Institut national de recherche en informatique et en automatique) Saclay and Paris, France July 16 - July 27, 2018	Cité internationale universitaire de Paris (CIUP)

Summary

This is the second part of the summer school that takes over from Part 1 in La Rochelle. We aim to teach the fundamental concepts and important developments in data science and natural language processing. The target audience are students having completed advanced classwork in mathematics, statistics, or computer science.

Organizing Institution

Inria, the French National Institute for computer science and applied mathematics, promotes scientific excellence for technology transfer and society. Graduates from the world's top universities, Inria's 2,600 employees rise to the challenges of digital sciences. Research at Inria is organised in ³project teams´ which bring together researchers with complementary skills to focus on specific scientific projects. With this open, agile model, Inria is able to explore original approaches with its partners in industry and academia and provide an efficient response to the multidisciplinary and application challenges of the digital transformation. The source of many innovations that add value and create jobs, Inria transfers expertise and research results to companies (startups, SMEs and major groups) in fields as diverse as healthcare, transport, energy, communications, security and privacy protection, smart cities and the factory of the future.

Lecturers

Jing-Rebecca Li (INRIA-Saclay, CMAP Ecole Polytechnique, France)

Zoltan Szabo(CMAP Ecole Polytechnique, France)

Xingyi Song(University of Sheffield, UK) (By videoconference)

Balazs Pinter (Eötvös Loránd University, Hungary)

Schedule

Important information, please read regularly!

Map of CIUP campus.

Those who are coming on their own on Sunday: please go to Fondation Deutsch de la Meurthe to pick up your room key and walk to Maison de Norvege (where the rooms are).
For emergency help on CIUP campus go to Poste de sécurité or call them 01 44 16 66 00.

Paris metro map

RER B map

Up to date timetable

Scientific program

Week 1
Data Science (Linear algebra, optimization, applications, kernels, classification, kernel PCA/CCA, dependency measures/distances, hypothesis testing, acceleration schemes.)

GATE (Text Engineering Platform)

Week 2
Natural Language Processing (NLP) (Foundations of NLP: corpora, tokenization, stemming, term vector representations, POS tagging, parsing, language models, stopwords, text classification and clustering, dialogue systems. Deep learning in NLP: recurrent neural networks, LSTM, word vector representations, end-to-end dialogue systems.)
Professional advising (CV, motivation letter, PhD scholarship application)

Download and install

1. GATE (General Architecture for Text Engineering): GATE Developer 8.5.1

2. Matlab: Text Analytics Toolbox free trial

3. Python:Anaconda scientific package

Practical Project: Text processing for Adult Attachment Interview (AAI).

The AAI protocol has standard questions 1 to 20, each question often includes many follow-up questions.

Here are some AAI transcripts: AAI Transcripts in text format

AAI_name.txt is a text file that separates each speaker's speech into paragraphs. The question numbers 1-20 (frequently question 14 is missing from the interviews) are indicated by "1.", "2.", ..., "20." The "0." indicates the paragraph is not part of the 20 questions+follow-up questions+answers.

AAI_name_label_JRL.txt labels the questions (1-20) and the speakers of all paragraphs and store the labelled interview in a tab separated file.

Download class material.

Python Jupyter Notebooks

Present your results on Friday July 27,2018.

1. Try some classification algorithms on the labelled paragraphs (by speaker, by question number, for example).

2. Analysis of the answers to one or more questions.

Cultural program

Week 1
French language and culture classes (Monday, Wednesday, 2:30pm-4:30pm, Inria-Saclay)

July 21 2018
Guided visit of Paris (lunch and dinner included)

Week 2
French language and culture classes (Monday, Wednesday, 2:30pm-4:30pm, Inria-Saclay)

Lodging

The students will be lodged at Cit¡é internationale universitaire de Paris

17, bd Jourdan, 75014 Paris. Breakfasts will be provided (July 16 to July 27).

Housing starts on Sunday July 15 and ends on Thursday Aug 2, 2018

Practical details

Location of classes:

Inria-Saclay (Building Alan Turing).
Massy-Palaiseay station is the closest station : take RER line B towards Saint-Rémy-lès-Chevreuse, getting off at Massy-Palaiseau. Walk to the front of the train and take the stairs. On the top of the stairs, walk a few steps on your left and go down the stairs on your right. Walk straight forward to the bus stop (bus 91.06, the last one). Take the bus 91.06 (B or C), and get off at the "Polytechnique Labo" station. The bus appears every 10 minutes.

RER B schedule
Bus 91.06AB schedule (summer)
Bus 91.06C schedule (summer)
Inria-Paris.
The Inria Paris research centre is located in the 12th arrondissement of Paris at 2 rue Simone Iff. Below, please find our contact information and directions for visiting. If your GPS cannot locate "rue Simone Iff", enter "41-43 rue du Charolais 75012 Paris”. You will arrive at the back of the buildings.

Metro
Gare de Lyon station - Lines 1 and 14
Dugommier station - Line 6
Montgallet station - Line 8

Lunches will be provided.

Transportation

Pass Navigo (5 zones transportation card for Paris and surrounding regions) will be provided for each student

Included Meeting at Paris train station Sunday July 15.
Lodging in Paris from July 15 - Aug 2.
Breakfasts from July 16 - July 27.
Lunches Monday - Friday from July 16 - July 20.
Lunches Monday - Friday from July 23 - July 27.
Guided visits in Paris on July 21.
5 zones transportation card for Paris and surrounding regions.
Scientific program.
French language and culture classes.

Not included

Dinners (the students can use the common kitchens to cook in the lodging).
Lunch on the weekends.
Transportation away from lodging at the end of the program.

Jing-Rebecca Li

Last modified: Tue Jul 24 07:01:01 GMT 2018

Included	Meeting at Paris train station Sunday July 15. Lodging in Paris from July 15 - Aug 2. Breakfasts from July 16 - July 27. Lunches Monday - Friday from July 16 - July 20. Lunches Monday - Friday from July 23 - July 27. Guided visits in Paris on July 21. 5 zones transportation card for Paris and surrounding regions. Scientific program. French language and culture classes.
Not included	Dinners (the students can use the common kitchens to cook in the lodging). Lunch on the weekends. Transportation away from lodging at the end of the program.