Figurative Language Resolution
Module Description
Course | Module Abbreviation | Credit Points |
---|---|---|
BA-2010[100%|75%] | CS-CL | 6 LP |
BA-2010[50%] | BS-CL | 6 LP |
BA-2010[25%] | BS-AC | 4 LP |
BA-2010 | AS-FL | 8 LP |
Master | SS-CL, SS-FAL | 8LP |
Lecturer | Katja Markert |
Module Type | |
Language | English |
First Session | 19.04.2023 |
Time and Place | Mittwoch, 10:15-11:45, INF 325 / SR 24 |
Commitment Period | tbd. |
Prerequisite for Participation
BA: Einfhrung in die Computerlinguistik, Semantik.
MA: keine.
Assessment
Content
Figurative Language such as metaphor, irony, metonymy or idioms, is not just frequent but also a fundamental cognitive mechanism that structures conceptual domains.
Psycholinguistic research showed that metaphorical framing influences human inference processes. (Thibodeau und Boroditsky, 2013).
The resolution of figurative language was for a long time far behind other NLP topics, with regards to robustness, scalability and evaluation standards. This has changed in the last years due to the IARPA metaphor program, regular "Metaphor in NLP" workshops and shared tasks in the recognition of most types of figurative language.
This seminar will look at linguistic and cognitive background to figurative language, the development of annotated corpora as well as algorithms for processing a wide variety of figurative language types, including metaphor, irony, metonymy and idioms.
The algorithms range from AI-based algorithms to approaches rooted in distributional semantics or neural and transformer-based approaches. We will also include multimodal and multilingual approaches.
Module Overview
Agenda
Date | Session | Materials |
Literature
Will be given out at the start of term.