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 Thursdays at 14:00 in B203 (Autumn 2021) 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 ​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 ​authenticated ZOOM. Please upload any attachments to the online presentation by following the instructions. Uploaded videos are available on the video page.

Presentations wanted:

Presentations offered:

• ​Serge Sharoff: Reliable classification of web genres

Seminar programme in the autumn semester 2021

date	program
16.9.	seminar programme for this semester
	Aleš Horák: ​RASLAN 2021 Call for Papers
23.9.	Vít Novotný: SIGIR 2021 and RANLP 2021
	Adam Rambousek: ​AHISTO project
30.9.	Michaela Denisová: Crosslingual embedding models
7.10.	Mikuláš Bankovič: Superresolution techniques for OCR
14.10.	Rastislav Papčo: Topic classificaton in web corpora
	Edoardo Signoroni: Corpus alignment by machine translation techniques
21.10.	Dalibor Bačovský: Improving the Subword Model of fastText
4.11.	Ondřej Sotolář: Facebook conversations classification
	Radoslav Sabol: TBA
11.11.	Tereza Vrabcová: TBA
	Adam Hájek: TBA
18.11.	Petr Zelina: TBA
	Samuel Špalek: TBA
25.11.	Marek Medveď: QA
	Kristína Němcová: TBA
2.12.	Tomáš Houfek: Information extraction from medical records
	Daniel Krátký: TBA
9.12.	Krištof Anetta, Mahmut Arslan: Electronic health records processing
	Ondřej Herman: TBA

Seminar programme in the spring semester 2021

date	program
2.3.	seminar programme for this semester
9.3.	Pavel Rychlý: projekt LINDAT/CLARIAH-CZ
	Pavel Rychlý: projekt strojového překladu
	Pavel Rychlý: projekt generování slovníku
16.3.	Helena Medková: Zeugma Detection using Word Sketch
	Vítek Novotný: EDS-MEMBED: Multi-Sense Embeddings Based on Enhanced Distributional Semantic Structures via a Graph Walk over Word Senses
23.3.	Michal Štefánik: Unsupervised Estimation of Out-of-Domain Performance of Language Models
	Marek Medveď: SQAD database update
30.3.	Hien Thi Ha: Block type classification from scanned invoices
	Vítek Novotný: Combining log-bilinear language models with Transformers
6.4.	Tomáš Houfek: Vytěžování dat z lékařských zpráv
13.4.	Mikuláš Bankovič: Application of super-resolution on OCR of historical documents
	Adam Hájek: výpočet GTP-2 na Metacentru
20.4.	Tereza Vrabcová: Parallel corpus from web pages
	Vítek Novotný: When FastText Pays Attention (​preprint)
27.4.	Tereza Kinská: Creation of Judikatura corpora of court decisions
	Pavel Rychlý: Using Makefiles for NLP projects
4.5.	Petr Zelina: ALBERT Training with TensorFlow and PyTorch
11.5.	Krištof Anetta: Electronic Health Records processing, Apache cTakes
18.5.	Ondřej Sotolář: Building a Corpus for Personal Data Detection
25.5.	Michal Starý: Event Detection

It is also possible to view the seminar programme in preceding semesters.