←
Marek Kubis54 posts
Marek Kubis avatar

Marek Kubis

@marekkubis

Assistant Professor at @poznanAI. Leader of Conversational Systems Team at the Center for Artificial Intelligence @UAM_Poznan. #AI #NLProc

◷ Joined January 2011▧ 2 Photos and videos
Department of Artificial Intelligence AMU Poznan avatar
⟳ Marek Kubis retweeted
Department of Artificial Intelligence AMU Poznan@poznanAI·16 Aug 2024

Today was tle last day of workshops at @aclmeeting conference. Yesterday at @wassa_ws, @PSkorzewski and @piotrjablo represented our department with paper „POLygraph: Polish Fake News Dataset” check full paper at aclanthology.org/2024.wassa-…

Department of Artificial Intelligence AMU Poznan avatar
⟳ Marek Kubis retweeted
Department of Artificial Intelligence AMU Poznan@poznanAI·4 Jul 2024

POLygraph - our team @PSkorzewski @marekkubis @FilipGralinski @piotrjablo and others, prepared a unique resource for fake news detection in Polish which will be presented at @wassa_ws workshop during @aclmeeting 2024 🚀🚀 Paper available at arxiv.org/abs/2407.01393 📄

Marek Kubis avatar
Marek Kubis@marekkubis·30 May 2024

Our work (@a_karlinska, @cezaryrosinski_, @marekkubis @patt_hub, @JanWieczorekPWr ) on using bibliodata LODification to create metadata-enriched literary corpora in line with FAIR principles is now available at aclanthology.org/2024.lrec-m…

Jacek Marciniak avatar
⟳ Marek Kubis retweeted
Jacek Marciniak@marjacek2·26 Jan 2024

We are participating in the aUPaEU workshop in Turin, Italy, on the presentation of the concept of the Agora. We are a part of a team developing  tools for collecting and searching of information for effective cooperation for scientists and HEIs in Europe. @WideningEU @poznanAI

Post attachmentPost attachmentPost attachment
Marek Kubis avatar
Marek Kubis@marekkubis·12 Dec 2023

Our work (co-authors: @PSkorzewski, Marcin Sowański, @tzietkiewicz) on using back transcription for evaluating robustness of #NLU models to speech recognition errors was featured on Samsung Research Blog research.samsung.com/blog/Ba… #AI #NLProc @poznanAI @samsungresearch

Marek Kubis avatar
Marek Kubis@marekkubis·27 Oct 2023

The robustness criteria that we formulate are then used to construct a model for detecting speech recognition errors that impact the NLU model in the most significant way.

Marek Kubis avatar
Marek Kubis@marekkubis·27 Oct 2023

Contrary to conventional adversarial attacks, which aim at determining the samples that deteriorate the model performance under study, our method also takes into consideration samples that change the NLU outcome in other ways.

Marek Kubis avatar
Marek Kubis@marekkubis·27 Oct 2023

The augmented dataset is used to evaluate natural language understanding models and the outcomes of the evaluation serve as a basis for defining the criteria of NLU model robustness.

Marek Kubis avatar
Marek Kubis@marekkubis·27 Oct 2023

The method that we propose relies on the use of back transcription, a procedure that combines a text-to-speech model with an automatic speech recognition system to prepare a dataset contaminated with speech recognition errors.

Marek Kubis avatar
Marek Kubis@marekkubis·27 Oct 2023

The preprint of our paper "Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors" accepted to #EMNLP2023 is now available at arxiv.org/abs/2310.16609 #NLProc #VoiceAI #AI