Academic year 2015-16
Intelligent Web Applications
| Degree: | Code: | Type: |
| Bachelor's Degree in Computer Science | 21449 | Optional subject |
| Bachelor's Degree in Telematics Engineering | 22623 | Optional subject |
| Bachelor's Degree in Audiovisual Systems Engineering | 21635 | Optional subject |
| ECTS credits: | 4 | Workload: | 100 hours | Trimester: | 1st |
| Department: | Dept. of Information and Communication Technologies |
| Coordinator: | Horacio Saggion |
| Teaching staff: | Horacio Saggion, Francesco Barbieri |
| Language: | Materials will be provided in English and teaching will be in Spanish unless specific requests from studets. |
| Timetable: | |
| Building: | Communication campus - Poblenou |
In AIW we will study techniques that will allow you to develop intelligent application (with emphasis on text-based applications).
Supervised and non-supervised techniques will be introduced assessing their advantages and disadvantages. Application to be studied include information extraction, opinion mining, and text summarization.
We will also explore topics such as text processing in social networks (Twitter) as well as study semantic repositories and linked data.
AIW requires knowledge of programming, data structures and algorithms, Knowledge of Java programming is desirable for the development of seminars and laboratory assignments.
Specific Skills Professionals
H1. Ability to design and carry out projects using computer own principles and methods of engineering.
Specific Skills Basic Training
B16-A. Knowing the theoretical
programming and use practical methods and languages
program development Systems software.
Specific skills of Computer Engineering
IN16. Knowing how the
general data networks and the Internet in particular.
IN7. Get data structures
basic and abstract data types, their properties and applications, and be able to determine the most appropriate for each situation.
Specific Skills Common to the branch of Telecommunications
T1. Ability to learn autonomously new knowledge and techniques suitable for
conception, development and exploitation of systems and telecommunication services.
Skills specific technology: Telematics
NT3. Ability to build, operate and
manage telematic services, including internet, web, architectural design (data and protocols), engineering
software technologies etc.
Skills specific technology: Audiovisual Systems
AU15. Gain basic knowledge
on data analysis, studying
its regularities, techniques
prediction and classification algorithms.
AU36. Master the main formalities of the representation of the content on the web and the ability to deploy a domain fragments of knowledge in these
formalism.
AU37. Know the basics data mining and web texts and ability to apply them to specific problems.
AU38. Mastering the techniques of the abstract
Multilingual Information System textual web in theory and in
practice.
AU39. Mastery of the advanced techniques
• Smart Smart Search information on the Web
Programming knowledge. Java. NLP or AI (desirable).
Instrumentals
G1 . Capacity for analysis and synthesis
G2 . Ability to organize and planning
G3 . Ability to apply knowledge to analyze situations and solve problems
G4 . Ability to search and information management
G5 . Skill in making decisions
G6 . Ability to communicate orally and property written in Catalan, Spanish and Engish ,both expert and audiences to amateurs. interpersonal G8 . Ability to teamwork systemic
G11 . Ability to apply flexibility and creativity acquired knowledge and adapt to new situations and contexts G12 . Ability to progress in the process of training and Learning mode autonomous and continuous
G14 . Capacity motivation technologies quality and achieving
G15 . Ability to generate new ideas
Theory:
Theory assignments: 20% of the final mark. 80% of all the assignments need to be returned to the teacher.
Labs:
Lab 1 (2 sessions), 20% of the final mark.
Lab 2 (2 sessions), 20% of the final mark.
Lab 3 (1 session), 20% of the final mark.
At least 40% of the mark in each lab assignment should be obtain to pass.
At the end of the course an interview with the students will take place to assess the participation of each person in a lab group.
NOTE: In case that in one (and only one) lab assignment a student gets less than 40% of the marks, there will be the possibility for upgrading the obtained mark. Labs cannot be recovered in July.
Seminars:
Correspond to 20% of the final mark. Students will deliver a series of exercises at the end of the seminar. At least 40% of the mark should be obtained in each seminar. Seminars are not recoverable activities.
Block I: Manipulation of textual data.
Block II: Applications with text.
Block III: Advanced topics.
| In class | Out of class | ||||
|---|---|---|---|---|---|
| Topics | Theory | Labs | Seminars | ||
|
Block I |
6 |
0 |
2 |
24 |
|
| Block II | 8 | 6 | 6 | 30 | |
|
Block III |
4 |
4 |
0 |
24 |
|
|
Final Exam |
|
|
|
|
|
|
Total: |
18 |
10 |
8 |
68 |
Total: 104 |
There are 3 types of classes: theory, seminars, and laboratories. Each theory has an associated seminar or laboratory.
Teachers present the theoretical basis using book material and/or scientific articles. The students should complement the with suggested reading. During the theory, a set of exercises will be proposed to be solved by the students. These exercises will be evaluated and the obtained mark will contribute to the final mark.
There are 4 seminar sessions. In the seminars a tutorial will be given related to a topic covered in theory. At the end of the seminar the students will deliver a set of exercise or the development of the seminar for its evaluation. The mark obtained contributes to the final mark.
There are 5 labs sessions which will be used to develop 3 assignments. In order to solve the assignments students should work in group of 2 (throughout the trimester). Enough time will be given for the students to fully develop the assignments. The mark obtained in each lab contributes to the final mark.
Basic Bibliography
Manning, C.D. Prabhakar Raghavan, Hinrich Schütze. Introduction to information retrieval. New York : Cambridge University Press, 2008
Haralambos Marmanis and Dmitry Babenko. Algorithms of the intelligent web. Manning Publications, 2009.
Segaran, programming collective intelligence : building smart web 2.0 applications. O'Reilly, 2007.
Complementary Bibliography
Ethem Alpaydin. 2010. Introduction to Machine Learning. Second Edition. MIT Press.
Baeza-Yates, R. thier Ribeiro-Neto. Modern information retrieval. Reading, Mass. : Addison-Wesley Longman, 1999
Bramer, M. Principles of Data Mining. Springer. 2007.
GATE user guide. Disponible en http://gate.ac.uk/sale/tao/split.html
Grigoris Antoniou and Frank van Harmelen. A Semantic Web primer. The MIT Press, 2008.
Jurafsky, Dan & Martin, James. Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, Upper Saddle River, N.J.: Pearson Prentice Hall, 2009
Mani, Inderjeet. Automatic Summarization. John Benjamins Publishing Company. 2001.
Manning, C.D. Prabhakar Raghavan, Hinrich Schütze. Introduction to information retrieval. New York: Cambridge University Press, 2008
Manning, Christopher D. & Schutze, H. Foundations of statistical natural language processing Cambridge, Mass.: MIT Press, 1999
Mitchell, Tom M. Machine learning. New York: McGraw-Hill, 1997.
Mitchell, Tom (2005) Generative and Discriminative Classifiers: Naive Bayes and Logistic Regression. Supplementary chapter for Mitchell, Tom (1997) Machine Learning. McGraw-Hill.
Pang, B. and Lillian Lee. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval 2(1-2), 2008.
Pazienza. M.T.. Information extraction: a multidisciplinary approach to an emerging information technology. Springer, 1997.
Ian H. Witten, Eibe Frank. Data mining : practical machine learning tools and techniques. Morgan Kaufman, 2005.
Other resources
Scientific articles. Software (GATE, WEKA, SUMMA, LINGPIPE, etc.). Data.