Assistant Professor at @poznanAI. Leader of Conversational Systems Team at the Center for Artificial Intelligence @UAM_Poznan. #AI #NLProc
Joined January 2011
- Tweets 54
- Following 340
- Followers 89
- Likes 645
2 Photos and videos
7 Nov 2024
My talk on LLM Evaluation presented at Data on Campus 2 (in Polish) youtu.be/i2wFqIsy-UE?si=ySJ_…
1
1
181
13 Sep 2024
Our joint study on augmenting spoken language corpora was presented at @FedCSIS
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. arxiv.org/abs/2406.07090
192
Marek Kubis retweeted
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-…
2
3
219
4 Jul 2024
We have created POLygraph, a dataset of Polish fake news. Details below:
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 📄
1
3
169
Marek Kubis retweeted
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 📄
2
7
369
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…
6
10
632
7 Feb 2024
The preprint of our paper "Two Approaches to Diachronic Normalization of Polish Texts" accepted to LaTeCH-CLfL 2024 is now available at arxiv.org/abs/2402.01300 #NLProc #DH
1
182
Marek Kubis retweeted
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
wmi.amu.edu.pl/zycie-naukowe…
2
1
251
Marek Kubis retweeted
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
2
1
360
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
3
2
370
Marek Kubis retweeted
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 arxiv.org/abs/2310.16609
2
5
279
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.
1
113
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.
101
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.
1
87
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
2
3
161
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.
1
112
7 Oct 2023
Our paper "Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors (@PSkorzewski, Marcin Sowański, @tzietkiewicz) just got accepted to the main track of #EMNLP2023!
2
15
565
2 Oct 2023
Researchers of the Center for Artificial Intelligence at the FedCSIS conference in Warsaw linkedin.com/pulse/researche…
1
142
Marek Kubis retweeted
20 Sep 2023
Workshop co-organized during @FedCSIS conference. Room was full ;-)
4
3
290
11 Sep 2023
Four of my students are going to discuss their research at @YRRSDS_Official. @poznanAI!
11 Sep 2023
And YRRSDS 2023 has started! Looking forward to all the roundtable discussions and keynotes from @verena_rieser @malihealikhani & David Traum - stay tuned 👏👏
2
147