{{{#!html
<input type="hidden" id="lang_version" value="cs/LaboratorniSeminar" />
<input type="hidden" id="title_name" value="NLP Seminar"/>
}}}

{{{#!html
<input type="hidden" id="lang_version" value="en/NLPSeminar" />
<input type="hidden" id="title_name" value="Seminář laboratoře zpracování přirozeného jazyka"/>
}}}

= NLP lab seminar =

The laboratory seminar is primarily meant to present the activities of the active laboratory members: what they are doing, what results they have, what problems they have, which subtasks they are not able to solve and would like to have a collaboration of someone else, etc. Occasionally, and rather rarely, presentations by related department members can also be expected.

The seminar is now held on '''Wednesdays at 12:00 in B203''' (Spring 2025) and is open to anyone interested in the subject (does not have to be active in the lab). It can also be taken as a course [https://is.muni.cz/course/fi/pv173 PV173 NLP Lab Seminar] and earn three credits for active participation, including presentation of your results (achieved in NLP Center projects or on a relevant issue). The seminar is given in English. Presentations can be in English, Czech or Slovak.

Selected presentations are also presented online at [https://cesnet.zoom.us/j/92417314815 authenticated ZOOM].
Please upload any attachments to the online presentation by following the [wiki:en/NLPSeminar/PresentationInstructions instructions]. Uploaded videos are available on the 
[wiki:en/NLPSeminar/Videos video page].

=== Presentations wanted: ===
 


=== Presentations offered: ===
 * Vojtěch Kovář: News in Lexical Computing

=== Seminar programme in the spring semester 2025 === #seminar_spring

|| '''date''' || '''programme''' ||
{{{#!th rowspan=4
'''19.2.'''
}}}
|| seminar programme for this semester ||
|| Ondřej Herman: announcement of [https://projects.sketchengine.eu/conll2025 Shared Task: Robust Word Sense Induction] ||
|| Aleš Horák: [wiki:/en/NLPCentre#News new sitting corner] in the NLP lab ||
|| Aleš Horák: [wiki:/en/NLPMatrix NLP Matrix] server for NLP lab members ||
{{{#!th rowspan=1
'''26.2.'''
}}}
|| David Porteš: Reproducible ML experiments using Kubernetes, Gitlab and DVC ||
{{{#!th rowspan=1
'''5.3.'''
}}}
|| Edoardo Signoroni: Efficient Architectures for Low-Resource Machine Translation ||
{{{#!th rowspan=1
'''12.3.'''
}}}
|| Anna Winklerova: Linguistic feature overview and analysis ||
{{{#!th rowspan=1
'''19.3.'''
}}}
|| Ota Mikusek: From natural language to corpus-query language ||
{{{#!th rowspan=1
'''26.3.'''
}}}
|| Radoslav Sabol: Fine-grained Propaganda training set construction ||
{{{#!th rowspan=1
'''2.4.'''
}}}
|| Kryštof Bednařík: Topic Extraction  ||
{{{#!th rowspan=1
'''9.4.'''
}}}
|| Filip Prochac: RAG chatbot ||
{{{#!th rowspan=1
'''16.4.'''
}}}
|| Petr Zelina: BERT-like models for medical token classification ||
{{{#!th rowspan=1
'''23.4.'''
}}}
|| Helena Medková: BERT model for Zeugma Detection ||
{{{#!th rowspan=1
'''30.4.'''
}}}
|| Yasir Yakup Demircan: Misconfiguration Detection with sec-certs Framework  ||
{{{#!th rowspan=2
'''7.5.'''
}}}
|| Ondra Herman: Trends on Word Senses ||
|| Vlasta Ohlidalova: POS tagging evaluation for Czech ||
{{{#!th rowspan=1
'''14.5.'''
}}}
|| Michaela Denisová: Evaluation of cross-lingual word embeddings without linguistic data ||


=== Seminar programme in the autumn semester 2024 === #seminar_autumn

|| '''date''' || '''programme''' ||
{{{#!th rowspan=4
'''23.9.'''
}}}
|| seminar programme for this semester ||
|| Aleš Horák: [https://nlp.fi.muni.cz/projects/opravidlo20/ Opravidlo 2.0 – Public Online Proofreading Service] 
|| Aleš Horák: ​[http://raslan2024.nlp-consulting.net RASLAN 2024] Call for Papers ||
|| Zuzana Nevěřilová: Scientist Night team call ||
{{{#!th rowspan=1
'''30.9.'''
}}}
|| Patrik Stano: Anaphora Resolution ||
{{{#!th rowspan=1
'''7.10.'''
}}}
|| Ondřej Valášek: Terminology Extraction Evaluation  ||
{{{#!th rowspan=1
'''14.10.'''
}}}
||  Filip Prochác: RAG chatbot ||
{{{#!th rowspan=1
'''21.10.'''
}}}
|| Vojtěch Formánek: Jailbreaking Empathy ||
{{{#!th rowspan=2
'''4.11.'''
}}}
|| Emma Bednaříková: [htdocs:seminar/bednarikova_langtok2024.pdf Language Identification on the token level]  ||
|| Edoardo Signoroni: Low-Resource Machine Translation ||
{{{#!th rowspan=1
'''11.11.'''
}}}
|| Petr Zelina: regex from examples using LLMs ||
{{{#!th rowspan=1
'''18.11.'''
}}}
|| Radoslav Sabol: Progress on Slama: Foundational Slavonic Large Language Model ||
{{{#!th rowspan=1
'''25.11.'''
}}}
|| Marek Hába: Comparing different taggers for French on Rapcor corpus  ||
{{{#!th rowspan=1
'''2.12.'''
}}}
|| Helena Medková: The Explainability of the ZeugBERT model predictions on the Zeugma detection use case  ||
{{{#!th rowspan=2
'''9.12.'''
}}}
|| Michaela Denisová: Aligning Sense-specific Word Embeddings  ||
|| Michal Spiegel: Improving Semantic Representation in LLMs  ||
{{{#!th rowspan=2
'''16.12.'''
}}}
||  David Porteš: Using speech prosody to guide LLM generation ||
|| Anna Winklerova: Item text features: engineering and evaluation of explanatory power ||





[[BR]]You may also look at the [[NLPSeminarHistory| seminar programme in preceding semesters]].