Language Processing and Information Extraction

Code:

PRODEI034

Acronym:

PLEI

Keywords
Classification	Keyword
OFICIAL	Intelligent Systems

Instance: 2010/2011 - 1S

Active?	Yes
Responsible unit:	Department of Informatics Engineering
Course/CS Responsible:	Doctoral Program in Informatics Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
PRODEI	6	Syllabus	1	-	7,5	70	200

Teaching language

Suitable for English-speaking students

Objectives

A significant amount of all the information that we currently deal with is being communicated and stored in natural language (e.g. scientific papers, laws, news, twitter messages). There is also a huge amount of semi-structured information that is constantly being produced as result of logging real-world events (e.g. e-commerce logs). Additionally, information is often produced and shared in networks of interlinked objects, which, as they evolve, also become sources of new information in their own right.

The question is: what can we do with all this information? How can we generate value from it?

The goal of this course is to provide students with the basic skills for exploring this wealth of information. The student will learn the fundamental techniques, tools and resources for natural language processing and information extraction. In the end of this course, the students will be able to design and implement systems for analyzing and extracting information expressed in natural language or in semi-structured format, stored in multimedia repositories and networks. The student will also be introduced to some automatic classification and machine learning techniques, which are useful for the practical development of language processing and information extraction systems.

Program

During the first part of the semester, students will have to attend to lectures about several language processing and information extraction topics. Then, for each of these topics, a set of problems will be given. Each student will chose one of those problems and will spend the rest of the semester researching and developing an appropriate solution. Such research work will be supported by the teacher on a one-to-one basis.

The program of the course includes:

* Basic Language Processing operations, and related tools and resources. Fundamentals of knowledge representation for language processing. Ambiguity in language.

* Language processing and information extraction applications. Use cases.

* Text Classification using machine learning techniques

* Information extraction from industrial media

* Information Extraction from user-generated contents

* Information extraction over social networks. Tagging and Folksnomies.

* Log Analysis, Pattern and Trend Detections, Recommendation

Alternatively, students can suggest additional topics to explore in their research work, if such topics are related to language processing and information extraction.

Mandatory literature

Christopher D. Manning And Hinrich Schütze; Foundations of Statistical Natural Language Processing, MIT-Press, 1999. ISBN: 0-262-13360-1

Teaching methods and learning activities

Students will have to attend lectures. Individual research work will be supported by the teacher on a one-to-one basis.

keywords

Technological sciences > Engineering > Computer engineering

Evaluation Type

Distributed evaluation without final exam

Assessment Components

Description	Type	Time (hours)	Weight (%)	End date
Attendance (estimated)	Participação presencial	57,00
Mid-Term Evaluation (Short Paper + Presentation)	Defesa pública de dissertação, de relatório de projeto ou estágio, ou de tese	43,00
Final Evaluation (Full Paper + Presentation)	Defesa pública de dissertação, de relatório de projeto ou estágio, ou de tese	102,00
	Total:	-	0,00

Eligibility for exams

Each student will be given a set of problems, from which he/she will select one. The student will be graded according to how he/she achieves the corresponding solution. More specifically, in this course we will be evaluating:

1) how the student researches and compares solutions already proposed for the problem at hand;

2) how the student proposes and implements a (possibly original) solution to the problem;

3) how the student evaluates the solution he/she proposes;

4) how the student proposes improvements to the initial solution, and also how he/she implements and evaluates such improvements;

5) how the student communicates to others the solution he/she developed.

The grades will be given according to the performance of the students in two specific evaluation points: one halfway through the semester (30%) and the other in the end of the semester (70%).

Mid-point evaluation:

1) The student will have to prepare a “short-paper” describing the first experiments in tackling the selected problem. This component is 20% of the final grade.

2) A short presentation (10 mins) about the work developed so far. This component is 10% of the final grade.

In the end of the semester:

3) A “full-paper”, written in english, describing the complete solution developed to the problem and the results of the corresponding evaluation experiments. This component is 45% of the final grade.

4) A public presentation (25 mins) and demonstration of the complete solution. This component is 25% of the final grade.
For successfully obtaining a final grade, the student will have to score at least 7 out of 20 in all these components.

Special assessment (TE, DA, ...)

Students under special evaluation constraints are allowed to skip lectures. However, they still have to make the public presentations described in the previous section and the final grades will be given according to evaluation criteria already described.

Classification improvement

Only the end-of-semester evaluation (70%) can be subject to grade improvement. The student will have to resubmit a new research work (i.e. full-paper) and make the corresponding public presentation.