Seminar: Grounding Language into the External Visual World - Details

Allgemeine Informationen

Veranstaltungsname	Seminar: Grounding Language into the External Visual World
Untertitel
Veranstaltungsnummer	8.3497
Semester	SoSe 2021
Aktuelle Anzahl der Teilnehmenden	117
Heimat-Einrichtung	LE Cognitive Science
Veranstaltungstyp	Seminar in der Kategorie Offizielle Lehrveranstaltungen
Erster Termin	Donnerstag, 15.04.2021 14:00 - 16:00
Art/Form
SWS	2
Sprache	Englisch
ECTS-Punkte	4

Lehrende

• Prof. Dr. Elia Bruni

Tutor/-in

• Juri Moriße

Räume und Zeiten

Keine Raumangabe

Donnerstag: 14:00 - 16:00, wöchentlich

Studienbereiche

• Veranstaltungen > Cognitive Science > Master-Programm
• Veranstaltungen > Cognitive Science > Bachelor-Programm
• Veranstaltungen > Interdisziplinäre Studiengänge > Sprache in Europa > Sprache und Kognition

Modulzuordnungen

• Bachelor of Science Informatik > CS-BWP-CL - (Computer)Linguistik, gültig ab WiSe 2019/20
• Bachelor of Science Mathematik > CS-BWP-CL - (Computer)Linguistik, gültig ab WiSe 2019/20
• Bachelor of Science Cognitive Science > CS-BWP-CL - (Computer)Linguistik, gültig ab WiSe 2019/20
• Master of Science Mathematik > CS-BWP-CL - (Computer)Linguistik, gültig ab WiSe 2019/20
• Master of Arts Sprache in Europa > X-SE-KOG07 - Sprache und Kognition

Kommentar/Beschreibung

Everyday interactions require a common understanding of language, i.e. for people to communicate effectively, words (for example ‘cat’) should invoke similar beliefs over physical concepts (what cats look like, the sounds they make, how they behave, what their skin feels like etc.). However, how this ‘common understanding’ emerges is still unclear. One appealing hypothesis is that language is tied to how we interact with the environment. As a result, meaning emerges by ‘grounding’ language in modalities in our environment (images, sounds, actions, etc.).

This course will review recent works in machine learning which bridges visual and natural language understanding through visually-grounded language learning tasks, e.g. through natural images (Visual Question Answering, Visual Dialog), or through interactions with virtual physical environments.

As the grounding problem requires an interdisciplinary attitude, this course aims to gather students with broad expertise in various fields -- machine learning, computer vision, natural language, neuroscience, and psychology -- and who are excited about this space of grounding and interactions.