Topic outline

  • Lectures

    Lecture schedule 2023:

    • 10 jan 1 Introduction & Project groups / Mikko Kurimo
    • 17 jan 2 Statistical language models / Mikko Kurimo
    • 24 jan 3 Sentence level processing / Mikko Kurimo
    • 31 jan 4 Word2vec /  Tiina Lindh-Knuutila
    • 07 feb 5 Neural language modeling and large language models / Mittul Singh
    • 14 feb 6 Morpheme-level processing / Mathias Creutz
    • 21 feb Exam week, no lecture
    • 28 feb 7 Speech recognition / Tamas Grosz
    • 07 mar 8 Chatbots and dialogue agents / Mikko Kurimo
    • 14 mar 9 Statistical machine translation / Jaakko Väyrynen
    • 21 mar 10 Neural machine translation / Stig-Arne Grönroos
    • 28 mar 11 LLM discussion and course conclusion / Aku Rouhe and Mikko Kurimo
    • 04 april (no lecture)
    • 18 april Exam

    Below you can find slides of 2022 lectures until they are substituted by 2023 ones as the course progresses. Lecture recordings will also be added here.

    • 10 Jan 2023 1: Introduction & Course content / Mikko Kurimo

    • File icon
      Lecture 1 slides (2023) File
      PDF-dokument

      Introduction to Statistical Natural Language Processing

      Course practicalities in 2023

      Lecture 1 in the course text books:

      • Manning-Schutze: Chapters 1-2 pp. 1-80

    • Assignment icon
      Lecture 1 exercise return box Assignment
      Not available unless: You belong to any group

      -What kind of Natural Language Processing applications have you used?
      -What is working well? What does not work?
      -What kind of future applications would be useful in your daily life?

      Please type or upload the notes from your breakout group discussion here, e.g. as a photo, text or pdf file to earn a lecture activity point.

    • 17 Jan 2023 2: Statistical language models / Mikko Kurimo


    • File icon
      Lecture 2 slides (2023) Revised File
      PDF-dokument
      • statistical language models and their applications
      • maximum likelihood estimation of n-grams
      • class-based n-grams
      • the main smoothing methods for n-grams
      • introduction to other statistical and neural language models

      Lecture 2 in the course text books:

      • Manning-Schutze: Chapter 6 pp. 191-228
      • Jurafsky-Martin 3rd (online) edition: Chapter 3 pp. 37-62 (and Chapter 7 pp.131-150 for simple NNLMs)

    • Assignment icon
      Lecture 2 A exercise return box (applications) Assignment
      Not available unless: You belong to any group

      List as many potential applications for statistical language models as you can!
      Typically they are tasks where you need the probability or to find the most probable word or sentence given some background information

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

    • Assignment icon
      Lecture 2 B exercise return box (Good-Turing) Assignment
      Not available unless: You belong to any group
      Watch a video where Prof. Jurafsky (Stanford) explains Good-Turing smoothing (between 02:00 – 08:45)
      • Click:
      • Or search for:”Good Turing video Jurafsky”
      • Answer briefly these 3 questions in a single file or  text field
      1. Estimate the prob. of catching next any new fish species, if you already got: 5 perch, 2 pike, 1 trout, 1 zander and 1 salmon?
      2. Estimate the prob. of catching next a salmon?
      3. What may cause practical problems when applying Good-Turing smoothing for rare words in large text corpora?

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

    • 24 Jan 2023 3: Sentence level processing / Mikko Kurimo


    • File icon
      Lecture 3 slides (2023) Final File
      PDF-dokument
      Not available unless: You belong to any group

      Part-of-Speech and Named Entity tagging

      Hidden Markov models and Viterbi algorithm

      Advanced tagging methods


      Lecture 3 in the course text books:

      • Manning - Schütze(1999). MIT Press. Chapters 9--12
      • Jurafsky-Martin 3rd (online) edition: Chapters 8--9

    • Assignment icon
      Lecture 3 exercise return box (HMM and Viterbi) Assignment
      Not available unless: You belong to any group

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

      Discuss with each other in breakout rooms and propose answers for these 3 questions:

      1. Finish the POS tagging by Viterbi search example by hand.
      - Return the values of the boxes and the final tag sequence. Either take a photo of your drawing, fill in the given ppt, or just type the values into the text box  
      2. Did everyone get the same tags? Is the result correct? Why / why not?
      3. What are the pros and cons of HMM tagger?

      All submissions, even incorrect or incomplete ones, will be awarded by one activity point.

    • 31 Jan 2023 4: Word2vec / Tiina Lindh-Knuutila


    • File icon
      Lecture 4 slides (2023) File
      PDF-dokument
      Not available unless: You belong to any group
      • distributional semantics
      • vector space models
      • word2vec
      • information retrieval

      Lecture 3 in the course text books:

      • Jurafsky-Martin 3rd (online) edition: Chapter 6

    • Assignment icon
      Lecture 4 exercise return box (word vectors) Assignment
      Not available unless: You belong to any group
      1. What are the benefits of distributional semantics?
      2. What kind of problems there might be?
      3. What kind of applications can you come up with using these models?

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

    • 07 feb 2023 5 Neural language modeling and Large language models / Mittul Singh

    • File icon
      Lecture 5 slides (2023) final File
      PDF-dokument
      Not available unless: You belong to any group

      NNLMs are discussed in Chapter 7 in the 2020 online version of Jurafsky - Martin book.

    • Assignment icon
      Lecture 5 exercise return box: Self-attention Assignment
      Not available unless: You belong to any group

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

    • 14 feb 2023 6 Morpheme-level processing / Mathias Creutz

    • File icon
      Lecture 6 slides (2023) File
      PDF-dokument
      Not available unless: You belong to any group

      Not all of these slides will be discussed during the lecture, but everything is useful reading, still.

      NOTE: There is no text book yet that would cover this stuff well, so read the slides carefully!

    • Assignment icon
      Lecture 6 exercise return box Assignment
      Make a submission

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

    • 21 Feb 2023: Exam week, no lecture


    • 28 feb 2023 7 Speech recognition / Tamas Grosz

    • File icon
      Lecture 7 slides (2023) File
      PDF-dokument
      Not available unless: You belong to any group

      Hybrid DNN-HMM architecture

      End-to-end architectures

      Applications


      Lecture 5 in the course text books:

      • Jurafsky-Martin 3rd (online) edition: Chapters 26

    • Assignment icon
      Lecture 7 exercise return box Assignment
      Not available unless: You belong to any group

      Calculate the WER and CER metrics by comparing the ASR hyp to the
      human transcript!

      ASR hyp: he then appeared in the episode smackdown
      Human transcript: he then appeared on an episode of smackdown

      Which metric measures the true accuracy better in your opinion and why?

      All submissions, even incorrect or incomplete ones, will be awarded one activity point.

    • 07 Mar 2023 8: Chatbots and dialogue agents / Mikko Kurimo


    • File icon
      Lecture 8 slides (2023) File
      PDF-dokument
      Not available unless: You belong to any group

      Rule-based and Corpus-based chatbots

      Retrieval and Machine Learning based chatbots

      Evaluation of chatbots


      More information in the course text books:

      • Jurafsky-Martin 3rd (online) edition: Chapter 24

    • Assignment icon
      Lecture 8 exercise return box Assignment
      Not available unless: You belong to any group

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

      1. Try ELIZA, When does it fail? How to improve it? https://www.eclecticenergies.com/ego/eliza http://psych.fullerton.edu/mbirnbaum/psych101/Eliza.htm  
      2. Try PARRY, When does it fail? How to improve it?  https://www.chatbots.org/chatbot/parry/ https://www.botlibre.com/browse?id=857177
      3. Try more chatbots or dialogue agents, How to automatically evaluate them? https://convai.huggingface.co/ https://www.chatbots.org/ https://chat.openai.com/chat
      4. What ethical issues do chatbots have? Any suggestions how to solve them?

    • 14 March 2023 9: Statistical machine translation / Jaakko Väyrynen


    • File icon
      Lecture 9 slides (2023) File
      PDF-dokument
      Not available unless: You belong to any group

      Lecture based on:

      • ˆ Chapter 13.2-13.4 in Manning & Schutze
      • ˆ Chapter 21 in the OLD Jurafsky & Martin: Speech and Language Processing
      • Chapter 11 in the NEW Jurafsky & Martin: Speech and Language Processing
      • ˆ Koehn: "Statistical Machine Translation", http://www.statmt.org/book/
    • Assignment icon
      Lecture 9 exercise return box Assignment
      Make a submission

      Please type or upload your answer here, e.g. as a photo, text or pdf file and earn a lecture activity point.

      Consider different levels of language and different kinds of source-target pairs:
        1. What would be easy/hard to translate with MT?
        2. Have you seen failed/succesful usage or applications of MT?


      1. 21 Mar 2023 10: Neural machine translation / Stig-Arne Grönroos


      2. File icon
        Lecture 10 slides (2023) File
        PDF-dokument
        Not available unless: You belong to any group

        NMT is discussed in Chapter 11 in the 2020 online version of Jurafsky - Martin book.

      3. Assignment icon
        Lecture 10 exercise return box Assignment
        Make a submission

      4. 28 Mar 2023 11: LLM discussion and course conclusion / Aku Rouhe  and Mikko Kurimo


      5. File icon
        Lecture 11 slides (2023) Conclusion File
        PDF-dokument
        • The contents of the course
        • Info about passing the course and grading
        • Info about the exam
        • Quick recap of previous lectures
    ◄ Previous section
    Course practicalities
    Next section ►
    Assignments