GP »Argument Mining - Automated Argument Extraction« (SS25)

In an era where information is abundant and often polarizing, the ability to extract, analyze, and evaluate arguments from textual data is more crucial than ever. Argument mining is a subfield of natural language processing (NLP) that focuses on identifying and structuring argumentative components such as claims, premises, and conclusions in written or spoken discourse. With applications in legal texts, online debates, policy-making, and misinformation detection, argument mining enhances critical thinking and decision-making by uncovering the underlying logical structure of arguments. This project aims at building a production-ready prototype for an argument mining pipeline.

Keywords

argument mining, natural language processing, pipeline, large language model

Study Program and Module Description

Master Digital Sciences (specialization Software Architecture) (see also module description in the study program web page)

Begin/End and Scheduling

20.03.2025 - August 2025. Organized as an agile project with sprints every 2 weeks. Workload depends on the type of project, will be clarified at kickoff.

Location

Room 1: KI-Labor 0503 (Building LC6, opposite main entrance of Schwalbe Arena. The KI Labor is usually locked (unlike other lecture halls). I will be there in time to let you in. If you arrive well before starting time, you best wait in one of the other lecture halls - there are plenty of rooms, usually not all occupied at once.), see also detailed directions

Room 2: COCO-S28 (Code & Context, Campus Köln Mülheim, Schanzenstr. 28, 4th floor, exact room will be determined ad hoc. Door is usually open, otherwise ring.)

Room 3: 1708 (Building LC4 (library building). Room 1708 is our lab office space, with enough room for small workshops. However, the room is only accessible with by transponder. Thereore, please be at the door left of the library entrance (where you see the label "Kriminalkommissariat", since the Gummersbach police criminal investigation unit is our office neighbour :-). I will fetch you there. Call me (+49 176 8072 2689) or a fellow student by mobile phone in case you should run late), see also detailed directions

Video conference link: https://th-koeln.zoom-x.de/j/4425088059?pwd=K3hQOXRFa0YzUmZYSVRIejlZRklKdz09&omn=63215898401 (only in exceptional cases and if explicitly communicated in advance for the day)

Miro Board used for brainstorming and planning our deliverables

During the module, you can use this Miro Board.

Discord Server for fast Communication

Discord has been proven as a very effective platform for information sharing, discussions, and consultations. Therefore, please join the ArchiLab Discord Server at https://discord.gg/YYNYb5whU8. Navigate to channel #rollenzuweisung and click on gp. Then you automatically get access to the channel(s) relevant for this module.

Content

• Project Description
• Grading
• Workshops
  • Thu 20.03.2025, 11:00 - 16:30: Kickoff Workshop
  • Tue 15.04.2025, 13:00 - 17:00: Literature & Getting Started
  • Tue 29.04.2025, 16:00 - 19:00: Data Selection & Architecture Workshop

Project Description

For the general project definition, please see the project page in the Master Digital Science web portal. As an introduction to the topic, please read Anthony’s Bachelor Thesis. This project is basically based on Anthony’s work in the BA, the several projects leading up to the thesis.

Grading

The grading for this Guided Project will follow the general grading scheme for Guided Projects outlined here.

Both the quality and the effort part of the grading will be based on

• commitment in contribution to the project (discussions, helping others, going the extra mile, offline work etc.)
• quality and effort in scientific research
• quality of model artefacts created in the project
• general architecture and code quality (where coding is involved)

Workshops

Thu 20.03.2025, 11:00 - 16:30: Kickoff Workshop

We brainstorm our findings so far, and plan our actions in the project.

Workshop Location

Room: KI-Labor 0503 (Building LC6, opposite main entrance of Schwalbe Arena. The KI Labor is usually locked (unlike other lecture halls). I will be there in time to let you in. If you arrive well before starting time, you best wait in one of the other lecture halls - there are plenty of rooms, usually not all occupied at once.), see also detailed directions. In addition, there is a video conference. Video conference link: https://th-koeln.zoom-x.de/j/4425088059?pwd=K3hQOXRFa0YzUmZYSVRIejlZRklKdz09&omn=63215898401

Goal of the day

The project is set up and ready to start.

Agenda

• 11:00 - 14:00:  Introduction
  • Foundations of this project
  • Introduction to argument mining
  • Goals and deliverables
  • (with lunchbreak in between)
• 14:00 - 14:30:  Organizational Issues
  • Meeting structure
  • Locations
  • Grading
• 14:30 - 16:30:  Planning
  • Mapping out the next 2-4 weeks of work
  • What to do first

Task until next workshop

• Set up a regular bi-weekly meeting
• Get up to speed with the topic at hand

Tue 15.04.2025, 13:00 - 17:00: Literature & Getting Started

Results from literature research, and planning of next steps

Workshop Location

Room: COCO-S28 (Code & Context, Campus Köln Mülheim, Schanzenstr. 28, 4th floor, exact room will be determined ad hoc. Door is usually open, otherwise ring.).

Goal of the day

Everyone knows what to do next

Agenda

• 13:00 - 17:00:  Research results and Planning
  • status update
  • presentation of research results
  • first design decisions
  • planning for next sprint

Task until next workshop

• Work on tasks as specified in our JIRA

Tue 29.04.2025, 16:00 - 19:00: Data Selection & Architecture Workshop

Presenting results from individual tasks, and architecture discussion

Workshop Location

Room: COCO-S28 (Code & Context, Campus Köln Mülheim, Schanzenstr. 28, 4th floor, exact room will be determined ad hoc. Door is usually open, otherwise ring.).

Goal of the day

Updates & decisions