German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz

Deutsch

Multilinguality and Language Technology

The research department Multilinguality and Language Technology (MLT) in Saarbrücken is headed by Prof. Dr. Josef van Genabith.

MLT covers the following main topics: Machine Translation (MT), Question Answering and Information Extraction Systems (QAIE), Talking Robots (TR), and Data and Resources (D&R).

MT group: Machine translation between texts and from text to sign language;
QAIE group: Highly scalable text analysis and, based on this, question-answering and information extraction systems;
TR group: Dialog processing for human-robot collaboration and for teamwork support. Basic dialog technologies as well as applications, e.g., for disaster response management and health care;
D&R group: Collection of language data and processing into resources for the development of intelligent language technologies.

We work with machine learning and knowledge-based approaches. Besides basic research, MLT is strongly involved in contract research and industrial projects.

At Saarland University, members of the MLT group are involved in leading positions in SFB 1102 (Information Density and Linguistic Encoding, subproject B6), a DFG project on multi-modal interfaces for post-editing of MT results (MMPE), and the “Erasmus Mundus European Masters Program in Language and Communication Technologies” (LCT).

TRADR

ELRC

QT21

Talks at MLT-Meetings

2022

Presenter	Affiliation	Title	Date
Maurice Rekrut	DFKI Saarbrücken	Anaphoric annotations for combined entities in recipes	Aug 29
Doreen Osmelak	Saarland University	Towards efficient dialogue processing in the emergency response domain	Aug 22
Rishu Kumar	DFKI Saarbrücken	Cross-lingual transfer learning with Persian	Aug 08
Anna Mochova	Saarland University	Exploring Mention Representations for Coreference Resolution in Dialogue	July 25
Aravind Krishnan	DFKI Saarbrücken	Multilingual Relation Classification via Efficient and Effective Prompting	July 18
Lonneke van der Plas	IDIAP Martigny	Cross-Lingual Transfer for Low-Resource Languages	July 11
Noon Pokaratsiri	DFKI Saarbrücken	Towards Understanding the Role of Graph Structures in Medical Codes Classification	July 04
Alina Leippert	DFKI Saarbrücken	Clarification Request Identification in Knowledge-based Question Answering	Jun 27
Rishu Kumar	DFKI Saarbrücken	Does multilingual training improve the performance for low resource language summarization?	Jun 13
Xudong Huong	Saarland University	Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences	May 30
Joseph Renner	INRIA & Sorbonne Université	Exploring Category Structure with Contextual Language Models and Lexical Semantic Networks	May 23
Matúš Pikuliak	Kempelen Institute of Intelligent Technologies	An In-Depth Look at Word Filling Societal Bias Measures	May 16
Natalia Skachkova	DFKI Saarbrücken	Prompting Large LMs with OpenPrompt	May 09
Tanja Bäumel	DFKI Saarbrücken	An Introduction to Explainable AI	May 02
Yusser Al-Ghussein	DFKI and Saarland University	Exploring Paracrawl for Document-level Neural Machine Translation	Apr 25
Michael Roth	Univ. Stuttgart	Language Understanding and Misunderstanding	Apr 18
Lukas Lange	Bosch Center for Artificial Intelligence	SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains	Apr 11
Urs Peter	DFKI and Saarland University	Co-reference Resolution in Low-Resource Annotation	Apr 04
Vanessa Camilleri	University of Malta	XR for training & Development - a look at the promises and ethical pitfalls of emerging tech for teaching and learning	Mar 28
Marta R. Costa-jussà	Meta AI	No-language-left-behind: Scaling Human-Centered Machine Translation* and Toxicity at Scale	Mar 14
Brielen Madureira Lasota	Uni Potsdam	What is going on at colab Potsdam — and why research on dialogue games is cool	Mar 07
Yasser Hamidullah	DFKI Saarbrücken	Sentence Embeddings as Joint Latent Space Linking Vision and Text in Sign Language Translation	Feb 22