Politechnika Warszawska - Centralny System Uwierzytelniania
Strona główna

Argument Technology

Informacje ogólne

Kod przedmiotu: 103A-xxxxx-MSA-EATEC
Kod Erasmus / ISCED: (brak danych) / (brak danych)
Nazwa przedmiotu: Argument Technology
Jednostka: Wydział Elektroniki i Technik Informacyjnych
Grupy: ( Courses in English )--eng.-EITI
( Non-Technical Electives )--M.Sc.-EITI
Punkty ECTS i inne: 3.00 Podstawowe informacje o zasadach przyporządkowania punktów ECTS:
  • roczny wymiar godzinowy nakładu pracy studenta konieczny do osiągnięcia zakładanych efektów uczenia się dla danego etapu studiów wynosi 1500-1800 h, co odpowiada 60 ECTS;
  • tygodniowy wymiar godzinowy nakładu pracy studenta wynosi 45 h;
  • 1 punkt ECTS odpowiada 25-30 godzinom pracy studenta potrzebnej do osiągnięcia zakładanych efektów uczenia się;
  • tygodniowy nakład pracy studenta konieczny do osiągnięcia zakładanych efektów uczenia się pozwala uzyskać 1,5 ECTS;
  • nakład pracy potrzebny do zaliczenia przedmiotu, któremu przypisano 3 ECTS, stanowi 10% semestralnego obciążenia studenta.
Język prowadzenia: angielski
Jednostka decyzyjna:

103000 - Wydział Elektroniki i Technik Informacyjnych

Kod wydziałowy:

EATEC

Numer wersji:

1

Skrócony opis:

Argument technology is a sub-field of Artificial Intelligence in which computational methods of creating, identifying, analysing, evaluating and visualising arguments and debates are employed. In the last couple of years, the growing interest in argument technologies may be observed, concurrently with the launch of the IBM’s Grand Challenge, Project Debater, the AI system that can debate humans in real time on a variety of complex topics. Contemporary advances in argument and debating technologies cover a wide range of research strands including the building of argument corpora and argument analytics for argument mining (the automated extraction of arguments from natural language data) and explainable AI.

Pełny opis:

Argument technology is a sub-field of Artificial Intelligence in which computational methods of creating, identifying, analysing, evaluating and visualising arguments and debates are employed. In the last couple of years, the growing interest in argument technologies may be observed, concurrently with the launch of the IBM’s Grand Challenge, Project Debater, the AI system that can debate humans in real time on a variety of complex topics. Contemporary advances in argument and debating technologies cover a wide range of research strands including the building of argument corpora and argument analytics for argument mining (the automated extraction of arguments from natural language data) and explainable AI.

The overarching aim of this course is to discuss and assess the current state of the art in the development of argument technology. To this end, a variety of research enterprises constituting theoretical foundations for argument technologies will be emphasised, such as argument mapping software, the corpora of annotated arguments for argument mining, the annotation of argument schemes, the annotation of appeals to speakers’ character (ethos), argument and ethos analytics. It will be shown how these and other activities may help building the Argument Web, an online ecosystem of tools, systems and services for argumentation.

In this way, a deeper insight into how argument technology is capable of making sense of a large-scale natural language data for understanding and predicting social processes will be obtained. Specifically, the need for understanding the complexity and multi-dimensionality of natural argumentation in dialogical context will be emphasized as a necessary condition for a further development of argument technology being capable of capturing the dynamics of arguments, and helping people build reasonable persuasive arguments, critically assess arguments, and make well-informed collective decisions in such areas as education, healthcare, policy making, intelligence analysis and risk management.

Curriculum:

  1. Introduction to argument technology: strands, models, methods, communities.
  2. From argument mapping to debating technologies: how argument visualisation (e.g. Rationale, Carneades) may help better understand AI systems to debate humans (Project Debater).
  3. Argumentation theory as a foundation for argument technology.
  4. Inference Anchoring Theory as a model frame for argument technology.
  5. OVA+ software as an online tool for representing dialogical arguments.
  6. Argument structures and argumentation schemes in OVA+.
  7. Profiles of dialogue and dialogue protocols in OVA+.
  8. Arvina: a mixed-initiative argumentation platform.
  9. Analysis and mining of ethos (character of the speaker).
  10. Corpora for ethos types.
  11. Ethotic arguments in the debates on contested cultural objects.
  12. Rephrase structures for argument technology.
  13. Argument and ethos analytics.
  14. Argument Web: an online ecosystem of tools, systems and services for argumentation
  15. Summary: towards making sense of social behaviour with argument technology.


Additional information

  1. Some meetings can be held online using Teams.
  2. The list of topics covered may vary slightly according to participants' preferences.
  3. During the course the open access software, Online Visualisation of Arguments, will be used.
Literatura:

  1. Budzynska, K., & Villata, S. (2017). Processing Natural Language Argumentation. In: P. Baroni, D. Gabbay, M. Giacomin, & L. van der Torre,
  2. Handbook of Formal Argumentation, London: College Publications, 576-625.
  3. Lawrence, J., Reed, C. (2019). Argument Mining: A Survey. Computational Linguistics, 45 (4): 765-818.
  4. Lawrence, J., Snaith, M., Konat, B., Budzynska, K., & Reed, C. (2017). Debating Technology for Dialogical Argument: Sensemaking, Engagement, and Analytics. ACM Transactions on Internet Technology, 17(3): 24:1-24:23.
  5. Reed, C., Budzynska, K., Duthie, R., Janier, M., Konat, B., Lawrence, J., Pease, A., Snaith, M. (2017). The Argument Web: An online ecosystem of tools, systems and services for argumentation. Philosophy and Technology, 30(2): 137-160.
  6. Slonim, N. et al. (2021). An Autonomous Debating System. Nature, 591: 379–384.
  7. Visser, J., Konat, B., Duthie, R., Koszowy, M., Budzynska, K., Reed, C. (2020). Argumentation in the 2016 US presidential elections: annotated corpora of television debates and social media reaction. Language Resources and Evaluation, 54: 123–154.
Metody i kryteria oceniania:

  1. Contribution to the discussion during the class (30%),
  2. argument technology related project devoted either to (1) the creation of a corpus of analysed arguments using OVA+ software, to be put in the access free database of argument corpora AIFdb, or to (2) writing an argumentative essay devoted to the critical assessment and future development of most recent achievements in argument technology (50%),
  3. participation in the class (20%).

Zajęcia w cyklu "rok akademicki 2024/2025 - sem. zimowy" (jeszcze nie rozpoczęty)

Okres: 2024-10-01 - 2025-02-16
Wybrany podział planu:
Przejdź do planu
Typ zajęć:
Ćwiczenia, 30 godzin, 20 miejsc więcej informacji
Koordynatorzy: Marcin Koszowy
Prowadzący grup: Marcin Koszowy
Lista studentów: (nie masz dostępu)
Zaliczenie: Ocena łączna
Jednostka realizująca:

118000 - Wydział Administracji i Nauk Społecznych

Opisy przedmiotów w USOS i USOSweb są chronione prawem autorskim.
Właścicielem praw autorskich jest Politechnika Warszawska.
pl. Politechniki 1, 00-661 Warszawa tel: (22) 234 7211 https://pw.edu.pl kontakt deklaracja dostępności USOSweb 7.0.0.0-7 (2024-03-18)