Information Retrieval & Natural Language Processing

Syllabus Outline

The site can be used for different purposes:

The course, in self-study modality  requires between 40 and 80 hours of study, depending on how much time is devoted to open exercises and suggested readings. It is recommended to organize the study into 8 study weeks. To work as an independent learner you should be able to effectively organize your time. A Study Guide (in preparation) and Contacts are provided to support your study with this distance learning material.
 

List of Syllabus Topics

1. Overview

2. Information Retrieval  (3 weeks)

  • Introduction
  • Indexing
  • Retrieval
  • Querying
  • Evaluation
  • Conclusions
  • 3. Natural Language Processing  for Information Retrieval  (3 weeks)

    • Introduction
    • Language Resources (Machine-Readable Dictionaries, Corpora, Lexical Databases, Semantic Networks)
    • Morphology and POS tagging
    • Phrasal and syntactic tagging
    • Sense tagging
    • Interactive Information Retrieval
    • Conclusions

    4. Cross-Language Information Retrieval  (2 weeks)

    • Introduction
    • Query Translation
      • Bilingual Dictionaries
      • Machine Translation
      • Bilingual Corpora
    • Alternative Approaches
      • Specific-purpose thesauri
      • Automatic Semantic Indexing
    • Conclusions

    Goals

    There are two aspects to what this course aims:
    1. Knowledge: you will learn about concepts, techniques, tools, and a variety of applications.

    2. Skills: you should develop practical abilities to achieve some tasks involving the use of a
    variety  of software tools.

    Syllabus topics (Description)

    Overview.
    An introduction to the topic and a motivation to get into it.

    Information Retrieval.
    A very basic review of the main issues and techniques related to the field of Information Retrieval.

    Natural Language Processing for Information Retrieval.
    A brief consideration of the potentialities of language technologies to improve text retrieval.

    Cross Language Information Retrieval.
    Cross-Language Information Retrieval, understood as a text retrieval problem where the query and the documents are expressed in different languages, is an area of research of growing importance that has brought language technologies to the attention of the text retrieval community. The greatest potential for Natural Language Processing in Information Retrieval seems to be here.