TUW NLP

The NLP research group at the Institute of Information Systems Engineering of TU Wien is an interdisciplinary team of natural language experts.

2024-11-19

At Language Intelligence 2024 Gábor Recski gave a talk on Fact-checking LLMs with explainable information extraction

2024-09-13

Our paper TPPMI - a Temporal Positive Pointwise Mutual Information Embedding of Words, based on the B.Sc. thesis of Paul Schmitt and a collaboration with RC2S2, was published at the 4th Workshop on Computational Linguistics for the Political and Social Sciences (CPSS) .

2024-09-11

Our paper Word alignment in Discourse Representation Structure parsing, based on the masters thesis of Christian Obereder, was presented at KONVENS 2024

2024-07-06

Our paper describing the creation of the BRISE-Plandok dataset was published in Language Resources and EvaluationBRISE-plandok: a German legal corpus of building regulations by Gábor Recski, Eszter Iklódi, Björn Lellmann, Ádám Kovács, and Allan Hanbury.

2024-06-21

Our group participated in the Semeval-2024 task on Hallucination detection. Read our paper TU Wien at SemEval-2024 Task 6: Unifying Model-Agnostic and Model-Aware Techniques for Hallucination Detection by Varvara Arzt, Mohammad Mahdi Azarbeik, Ilya Lasy, Tilman Kerl, and Gábor Recski.

2024-02-16

Gábor Recski was one of the keynote speakers at the IRI§24 – International Legal Informatics Symposion

2023-11-10

Gábor Recski gave a keynote presentation on the potentials of NLP in analyzing parliamentary records, at the workshop Fachtagung Spracherkennung organized by the Austrian Parliament

2023-11-08

What can AI do for Advanced Legal Research? was the title of a keynote presentation given by Gábor Recski at the Law via the Internet Conference

2023-01-09

Our paper on Offensive text detection across languages and datasets using rule-based and hybrid methods, presented by Kinga Gémes at AIMLAI at CIKM, has just been published in the workshop's proceedings, here.

2022-10-19

POTATO at CIKM'22 — Adam presented the exPlainable infOrmation exTrAcTion framewOrk at the demo session of CIKM in Atlanta. Read our paper here.

2022-02-28

Explainable lexical entailment with semantic graphs — Our article has been published in Natural Language Engineering. It is available under Open Access here.

2022-02-04

POTATO on TDS — Adam published a blogpost about POTATO on Towards Data Science

2022-01-25

POTATO release 0.0.8 — For our submission to the ACL 2022 Demo track we have released a new version of the POTATO framework

2022-01-18

POTATO presentation — Adam presented the POTATO tool at our first seminar of 2022, there's a video, slides, and a paper.