Human Language Engineering

You are here

Home » Studies » Masters » Master in Data Science » Curriculum » Syllabus » Human Language Engineering
Credits
4.5
Types
  • MDS: Elective
  • MAI: Elective
Requirements
This subject has not requirements, but it has got previous capacities
Department
CS;TSC
Human Language Engineering constitutes a broad field. The aim of this course is first to provide the students with a general overview of the range of applications associated with language engineering, identifying the currents trends. After this overview, the course will be centered on three specific areas: Information Extraction, Machine Translation and Dialogue Systems. For each area, some applications has been selected to work on. Students will learn what knowledge and tools needs an engineer to develep such applications. Current applications from companies will be presented to understand the present situation of Human Language Engineering at the market.

Teachers

Person in charge

  • Anna Sallés Rius ( )

Weekly hours

Theory
2
Problems
1
Laboratory
0
Guided learning
0
Autonomous learning
5.65

Competences

Generic Technical Competences

Generic

  • CG1 - Capability to plan, design and implement products, processes, services and facilities in all areas of Artificial Intelligence.

Technical Competences of each Specialization

Academic

  • CEA3 - Capability to understand the basic operation principles of Machine Learning main techniques, and to know how to use on the environment of an intelligent system or service.
  • CEA5 - Capability to understand the basic operation principles of Natural Language Processing main techniques, and to know how to use in the environment of an intelligent system or service.
  • CEA7 - Capability to understand the problems, and the solutions to problems in the professional practice of Artificial Intelligence application in business and industry environment.

Professional

  • CEP3 - Capacity for applying Artificial Intelligence techniques in technological and industrial environments to improve quality and productivity.
  • CEP4 - Capability to design, write and report about computer science projects in the specific area of ??Artificial Intelligence.

Transversal Competences

Teamwork

  • CT3 - Ability to work as a member of an interdisciplinary team, as a normal member or performing direction tasks, in order to develop projects with pragmatism and sense of responsibility, making commitments taking into account the available resources.

Information literacy

  • CT4 - Capacity for managing the acquisition, the structuring, analysis and visualization of data and information in the field of specialisation, and for critically assessing the results of this management.

Reasoning

  • CT6 - Capability to evaluate and analyze on a reasoned and critical way about situations, projects, proposals, reports and scientific-technical surveys. Capability to argue the reasons that explain or justify such situations, proposals, etc..

Analisis y sintesis

  • CT7 - Capability to analyze and solve complex technical problems.

Basic

  • CB6 - Ability to apply the acquired knowledge and capacity for solving problems in new or unknown environments within broader (or multidisciplinary) contexts related to their area of study.
  • CB8 - Capability to communicate their conclusions, and the knowledge and rationale underpinning these, to both skilled and unskilled public in a clear and unambiguous way.
  • CB9 - Possession of the learning skills that enable the students to continue studying in a way that will be mainly self-directed or autonomous.

Objectives

  1. Learning the current trends of Human Language Engineering and further challenges.
    Related competences: CEA3, CEA5, CEA7, CG1, CT4, CB9,
  2. Learning knowledge and tools required to develop Human Language Engineering applications in the selected areas (Information Extraction, Machine Translation and Dialogue Systems), and comparison criteria.
    Related competences: CEA3, CT4, CT6, CB8,
  3. Development of criteria to identity problems to be solved using Human Language Engineering.
    Related competences: CEA7, CG1, CEP3, CT3, CT6, CT7,
  4. Application of the acquired knowledge to specific real problems.
    Related competences: CEA3, CEA5, CEA7, CG1, CEP3, CEP4, CT3, CT7, CB6,
  5. Understanding the potential applications of Human Language Engineering in the business environment.
    Related competences: CEA3, CEA5, CEA7, CG1,

Contents

  1. Course Introduction
    Presentation of the course: aims, plan and structure.
    General overview of the range of applications associated with language engineering. Currents trends.
  2. Information Extraction
    Entity and Relation extraction. Event and Time extraction. Sentiment and Affect extraction. Summarisation.
  3. Machine Translation
    Classical MT. Statistical MT. Resources and models for MT. MT Evaluation.
  4. Dialogue Systems
    Question Answering. Conversational Agents. Chatbots. Virtual Assistants.

Activities

Activity Evaluation act


Course Introduction

Presentation of the course: aims, plan and structure. General overview of the range of applications associated with language engineering. Currents trends.
Objectives: 1
Contents:
Theory
2h
Problems
1h
Laboratory
0h
Guided learning
0h
Autonomous learning
5.7h

Information Extraction

Entity and Relation extraction. Event and Time extraction. Sentiment and Affect extraction. Summarisation. Considering open and restricted domains. Considering monolingual and crosslingual scenarios.
Objectives: 5 2 3
Contents:
Theory
6h
Problems
3h
Laboratory
0h
Guided learning
0h
Autonomous learning
17h

Machine Translation

Classical MT. Statistical MT. Resources and models for MT. MT Evaluation. Text-to-text translation. Speech-to-speech translation.
Objectives: 5 2 3
Contents:
Theory
8h
Problems
4h
Laboratory
0h
Guided learning
0h
Autonomous learning
22.6h

Dialogue Systems

Question Answering. Conversational Agents. Chatbots. Virtual Assistants.
Objectives: 5 2 3
Contents:
Theory
6h
Problems
3h
Laboratory
0h
Guided learning
0h
Autonomous learning
17h

Industrial presentations

Industrial presentations: learning current applications of human language engineering.
Objectives: 3 4
Contents:
Theory
2h
Problems
1h
Laboratory
0h
Guided learning
0h
Autonomous learning
5.7h

Students presentations

Students presentations: oral presentation of the study or development carried on.
Objectives: 3 4
Contents:
Theory
2h
Problems
1h
Laboratory
0h
Guided learning
0h
Autonomous learning
5.7h

Teaching methodology

This course will build on different teaching methodology (TM) aspects, including:

TM1: theoretical lecture sessions
TM2: practical sessions with invited speakers from the industry
TM3: oral presentations of the students

Evaluation methodology

The students must deliver a report from three practical sessions where invited speakers from the industry explain actual applications of HLE. Only three industrial sessions will be subject of reporting, even in the case that some additional sessions would be scheduled.

Each report is the 10% of the final mark.

For the other 70% of the mark, each student will choose one option among:

1. Deep study of a specific HLE application or a comparative study of HLE applications
2. Development of a HLE application
3. Development of a proposal to solve a specific real challenge

In all the cases, a preliminar deliverable will be required (10%), as well as a final report (50%),
and an oral presentation (10%).

Bibliography

Basic:

Previous capacities

- Introductory concepts and methods of Natural Language Processing.

- Programming.