PALS0039 Introduction to Deep Learning for Speech and Language Processing
UCL Division of Psychology and Language Sciences

Week 9 - Human-Machine Dialogue Systems

In which we discuss neural network systems for holding a conversation and answering questions.

Learning Objectives

By the end of the session the student will be able to:


Today's lecture is given by Christos Christodoulopoulos from Amazon Cambridge.

  1. History of dialogue systems
  2. We present a brief history of dialogue systems from early text understanding in micro-worlds through to chatbots and conversational agents like Alexa and Siri. We discuss the 'Turing test' as a gold standard for human-machine dialogue.

  3. Dialogue system architecture
  4. We discuss the components of a typical dialog system, comprising speech recognition, natural language understanding, dialogue manager, natural language generation and text to speech.

  5. Question Answering
  6. We address the problem of finding the answers to questions posed by users from a knowledgebase. Firstly queries are converted to some logical form through semantic parsing, then the logical form is used to retrieve matching data in a structured database of facts.

  7. Semantic parsing of disfluent speech
  8. Natural speech is full of disfluencies. We discuss how the intention of the user can be established despite disfluency.

  9. End-to-end neural data-to-text generation
  10. We discuss emerging methods for neural text generation which operate directly from source data.

  11. Fact verification
  12. We discuss the ongoing challenge to verify statements made by users as supported or unsupported by evidence.

Research Paper of the Week

Web Resources


Be sure to read one or more of these discussions of dialogue system construction:


Implement answers to the problems described in the notebooks below. Save your completed notebooks into your personal Google Drive account.

To be announced...

Word count: . Last modified: 22:45 11-Mar-2022.