Advanced Human Languages Technologies

Credits
5
Types
  • MAI: Elective
  • MIRI: Elective
Requirements
This subject has not requirements , but it has got previous capacities
Department
CS;TSC
Web
https://www.cs.upc.edu/~padro/ahlt/ahlt.html
This course offers an in-depth coverage of main basic tasks for Natural Language Processing. We will present fundamental models and tools to approach a variety of Natural Language Processing tasks, ranging from named entity recognition to syntactic processing and document classification. The flow of the course is along two main axis: (1) computational formalisms to describe natural language processes, and (2) statistical and machine learning methods to acquire linguistic models from large data collections and solve specific linguistic tasks

Teachers

Person in charge

Weekly hours

Theory
1.5
Problems
0.5
Laboratory
1
Guided learning
0
Autonomous learning
5.3333

Competences

Generic Technical Competences

Generic

  • CG3 - Capacity for modeling, calculation, simulation, development and implementation in technology and company engineering centers, particularly in research, development and innovation in all areas related to 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.
  • CEA10 - Capability to understand advanced techniques of Human-Computer Interaction, and to know how to design, implement and apply these techniques in the development of intelligent applications, services or systems.

    • 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.

    • 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. Learn to apply statistical methods for NLP in a practical application
      Related competences: CB6, CB8, CT3, CEA10, CEA3, CEA5, CEA7,
    2. Understand statistical and machine learning techniques applied to NLP
      Related competences: CT6, CT7, CEA3, CEP3, CG3, CB6,
    3. Develop the ability to solve technical problems related to statistical and algorithmic problems in NLP
      Related competences: CB6, CB8, CB9, CT7, CEA10, CEA3, CEA5, CEA7, CG3,
    4. Understand fundamental methods of Natural Language Processing from a computational perspective
      Related competences: CB6, CT7, CEA5, CEP4,

    Contents

    1. Statistical Models for NLP
      Introduction to statistical modelling for language. Maximum Likelhood models and smooting. Maximum entropy estimation. Log-Linear models
    2. Distances and Similarities
      Distances (and similarities) between linguistic units. Textual, Semantic, and Distributional distances. Semantic spaces (WN, Wikipedia, Freebase, Dbpedia).
    3. Sequence Predicion
      Prediction in word sequences: PoS tagging, NERC. Local classifiers, HMM, global predictors, Log-linear models.
    4. Syntactic Parsing
      Parsing constituent trees: PCFG, CKY vs Inside/outside
      Parsing dependency trees: CRFs for parsing. Earley algorithm
    5. Word Embeddings
      Static word embeddings. Word2Vec, Glove
      Limitations - need of contextual embeddings
    6. Recurrent Neural Networks
      RNNs for Language Modeling and sequence labeling
      Bottleneck problem. LSTMs
      Vanishing gradient problem
      LSTM-based word embeddings: ELMO
    7. Convolutional Neural Networks
      CNNs for NLP. 1D kernels vs 2D kernels.
      stride, padding
      Pooling
      NLP tasks suitable for CNNs vs RNNs
    8. Transformers
      Vanishing gradient problem in RNN/LSTM
      Attention
      Tranformer architecture
    9. Large Language Models
      Large Language Models: origin and evolution
      Reinforcement Learning from Human Feedback
      Fundational vs Instructed LLMs
      Use of LLMs in NLP applications: Zero shot, few-shot, fine-tuning
      Optimization and efficiency issues
    10. Ethics - Limitations and Risks of LLMs
      Biases
      Hallucinations
      Security
      Environmental costs
      Social costs

    Activities

    Activity Evaluation act


    Statistical Language Models

    Introduction to statistical modelling for language. Maximum Likelhood models and smooting. Maximum entropy estimation. Log-Linear models
    Objectives: 4 2
    Contents:
    Theory
    2.5h
    Problems
    0.5h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Distances and Similarities

    Distances (and similarities) between linguistic units. Textual, Semantic, and Distributional distances. Semantic spaces (WN, Wikipedia, Freebase, Dbpedia). Latent Semantic Analysis. Word Embeddings
    Objectives: 4 2
    Contents:
    Theory
    2h
    Problems
    0.5h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Sequence Prediction

    These lectures will present sequence labeling models, an important set of tools that is used for sequential tasks. We will present this in the framework of structured prediction (later in the course we will see that the same framework is used for parsing and translation). We will focus on machine learning aspects, as well as algorithmic aspects. We will give special emphasis to Conditional Random Fields.
    Objectives: 4 2
    Contents:
    Theory
    2h
    Problems
    1h
    Laboratory
    4h
    Guided learning
    0h
    Autonomous learning
    8h

    Syntax and Parsing

    We will present statistical models for syntactic structure, and in general tree structures. The focus will be on probabilistic context-free grammars and dependency grammars, two standard formalisms. We will see relevant algorithms, as well as methods to learn grammars from data based on the structured prediction framework.
    Objectives: 4 2
    Contents:
    Theory
    3h
    Problems
    1h
    Laboratory
    4h
    Guided learning
    0h
    Autonomous learning
    8h

    Word Embeedings

    Static Word embeddings. Word2Vec, Glove, FastText
    Objectives: 4 2
    Contents:
    Theory
    2h
    Problems
    0.5h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Recurrent Neural Networks

    Recurrent Neural Networks. Bottleneck problem. LSTMs. Vanishing Gradient problem
    Objectives: 4 2
    Contents:
    Theory
    2h
    Problems
    1h
    Laboratory
    4h
    Guided learning
    0h
    Autonomous learning
    8h

    Convolutional Neural Networks

    CNNs for NLP. 1D kernels vs 2D kernels stride, padding, pooling
    Objectives: 2
    Contents:
    Theory
    2h
    Problems
    1h
    Laboratory
    3h
    Guided learning
    0h
    Autonomous learning
    6h

    Transformers

    Attention. Transformers
    Objectives: 3
    Contents:
    Theory
    2h
    Problems
    1h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    3h

    Large Language Models

    Large Language Models. Origin & Evolution. Usage: zero-shot, few-shot, fine tuning optimization
    Objectives: 3 1
    Contents:
    Theory
    3h
    Problems
    1h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    2h

    Lab project


    Objectives: 3 1
    Week: 15 (Outside class hours)
    Theory
    0h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Final exam



    Week: 15 (Outside class hours)
    Theory
    0h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Teaching methodology

    The course will be structured around four different linguistic analysis levels: word level, phrase level, sentence level, and document level. Typical NLP tasks and solutions corresponding to each level will be presented.
    The first half of the course is devoted to "classical" statistical and ML approaches. The second half of the course revisits the same levels under a deep learning perspective

    Theoretical background and practical exercises will be developed in class.

    Finally, students will develop a practical project in teams of two students. The goal of the project is to put into practice the methods learned in class, and learn how the experimental methodology that is used in the NLP field. Students have to identify existing components (i.e. data and tools) that can be used to build a system, and perform experiments in order to perform empirical analysis of some statistical NLP method.

    Evaluation methodology

    Final grade = 0.5*FE + 0.5*LP

    where

    FE is the grade of the final exam

    LP is the grade of the lab project

    Bibliography

    Basic

    Web links

    Previous capacities

    - Although not mandatory, familiarity with basic concepts and methods of Natural Language Processing is strongly recommended

    - Good understanding of basic concepts and methods of Machine Learning.

    - Advanced programming skills.