Marek Kubis

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

[Marek Kubis @marekkubis]

@fbk_mt @Maureendss @EeshanDhekane Where can I find this paper? Is it available on Arxiv?

[Marek Kubis @marekkubis]

@piotrsankowski W Niemczech od lat działa DFKI, więc w żadnym sensie szybszy Pan nie był. Dziwne, ze Pan tego nie wie. https://t.co/CZEKozSkv0

[Marek Kubis @marekkubis]

@trajektoriePL @AlexObuchowski @mar_kar_ @rzeczpospolita Cóż. Wychodzi na to, że badania z zakresu lingwistyki komputerowej ze względu na popularność LLMów trafiły już do kategorii "amerykańscy naukowcy odkryli...".

[Marek Kubis @marekkubis]

@AlexObuchowski "języki wysokiego zasobu"😂

[Marek Kubis @marekkubis]

My talk on LLM Evaluation presented at Data on Campus 2 (in Polish) https://t.co/ldcmILURT6

[Marek Kubis @marekkubis]

Our joint study on augmenting spoken language corpora was presented at @FedCSIS

[Department of Artificial Intelligence AMU Poznan @poznanAI]

A joint study by @poznanAI researchers and Samsung Electronics Polska engineers was presented at @FedCSIS 2024. The paper investigates the impact of augmenting spoken language corpora with domain-specific synthetic samples. https://t.co/NhkDOc7xI2

[Department of Artificial Intelligence AMU Poznan @poznanAI]

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 https://t.co/6oVaclxz9a

[Marek Kubis @marekkubis]

We have created POLygraph, a dataset of Polish fake news. Details below:

[Department of Artificial Intelligence AMU Poznan @poznanAI]

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 https://t.co/PWcG5Hxztq 📄

[Department of Artificial Intelligence AMU Poznan @poznanAI]

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 https://t.co/PWcG5Hxztq 📄

[Marek Kubis @marekkubis]

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 https://t.co/f5K7RdBvhq

[Marek Kubis @marekkubis]

The preprint of our paper "Two Approaches to Diachronic Normalization of Polish Texts" accepted to LaTeCH-CLfL 2024 is now available at https://t.co/SHvyyMRTB5 #NLProc #DH

[Department of Artificial Intelligence AMU Poznan @poznanAI]

In exactly 20 minutes @marekkubis @PSkorzewski @tzietkiewicz and Marcin Sowański will speak about Back Transcription as a Method for Evaluating Robustness of NLU Models to Speech Recognition Errors. Join us online or in person. We start at 11.00 am CET
https://t.co/jvRwpvJUuj

[Jacek Marciniak @marjacek2]

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

[Marek Kubis @marekkubis]

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 https://t.co/tB8B5PkvEI #AI #NLProc @poznanAI @samsungresearch

[Department of Artificial Intelligence AMU Poznan @poznanAI]

A joint study of @UAM_Poznan researchers and Samsung Electronics Poland engineers on evaluating robustness of #NLU models to speech recognition errors was presented at #EMNLP2023 by @marekkubis and @tzietkiewicz https://t.co/bPTMuUX65L

[Marek Kubis @marekkubis]

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 @marekkubis]

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 @marekkubis]

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 @marekkubis]

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 @marekkubis]

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 https://t.co/1PoOzgPd3V #NLProc #VoiceAI #AI