|
Size: 5883
Comment:
|
← Revision 810 as of 2026-08-20 08:58:55 ⇥
Size: 4735
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 3: | Line 3: |
| = Natural Language Processing Seminar 2019–2020 = | = Natural Language Processing Seminar 2026–2027 = |
| Line 5: | Line 5: |
| ||<style="border:0;padding-bottom:10px">The NLP Seminar is organised by the [[http://nlp.ipipan.waw.pl/|Linguistic Engineering Group]] at the [[http://www.ipipan.waw.pl/en/|Institute of Computer Science]], [[http://www.pan.pl/index.php?newlang=english|Polish Academy of Sciences]] (ICS PAS). It takes place on (some) Mondays, normally at 10:15 am, in the seminar room of the ICS PAS (ul. Jana Kazimierza 5, Warszawa). All recorded talks are available [[https://www.youtube.com/channel/UC5PEPpMqjAr7Pgdvq0wRn0w|on YouTube]]. ||<style="border:0;padding-left:30px">[[seminarium|{{attachment:seminar-archive/pl.png}}]]|| | ||<style="border:0;padding-bottom:10px">The NLP Seminar is organised by the [[http://nlp.ipipan.waw.pjl/|Linguistic Engineering Group]] at the [[http://www.ipipan.waw.pl/en/|Institute of Computer Science]], [[http://www.pan.pl/index.php?newlang=english|Polish Academy of Sciences]] (ICS PAS). It takes place on (some) Mondays, usually at 10:15 am, often online – please use the link next to the presentation title. All recorded talks are available on [[https://www.youtube.com/ipipan|YouTube]]. ||<style="border:0;padding-left:30px">[[seminarium|{{attachment:seminar-archive/pl.png}}]]|| |
| Line 7: | Line 7: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''23 September 2019'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Igor Boguslavsky''' (Institute for Information Transmission Problems, Russian Academy of Sciences / Universidad Politécnica de Madrid)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Semantic analysis based on inference'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk delivered in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:5px">I will present a semantic analyzer SemETAP, which is a module of a linguistic processor ETAP designed to perform analysis and generation of NL texts. We proceed from the assumption that the depth of understanding is determined by the number and quality of inferences we can draw from the text. Extensive use of background knowledge and inferences permits to extract implicit information.|| ||<style="border:0;padding-left:30px;padding-bottom:0px">Salient features of SemETAP include: || ||<style="border:0;padding-left:30px;padding-bottom:0px">— knowledge base contains both linguistic and background knowledge;|| ||<style="border:0;padding-left:30px;padding-bottom:0px">— inference types include strict entailments and plausible expectations; || ||<style="border:0;padding-left:30px;padding-bottom:0px">— words and concepts of the ontology may be supplied with explicit decompositions for inference purposes; || ||<style="border:0;padding-left:30px;padding-bottom:0px">— two levels of semantic structure are distinguished. Basic semantic structure (BSemS) interprets the text in terms of ontological elements. Enhanced semantic structure (EnSemS) extends BSemS by means of a series of inferences; || ||<style="border:0;padding-left:30px;padding-bottom:15px">— a new logical formalism Etalog is developed in which all inference rules are written.|| |
||<style="border:0;padding-top:5px;padding-bottom:5px">'''7 September 2026'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Varvara Magomedova''' (University of Nova Gorica)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">[[http://zil.ipipan.waw.pl/seminarium-online|{{attachment:seminarium-archiwum/teams.png}}]] '''Veje – a future treebank of Slovenian dialectal texts'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Slovenian dialect research has produced a lot of literature, but not as many data sources. The lack of available syntactically annotated corpora limits research for those, who do not have access to native speakers. This talk presents the first phase of Veje – to become a Slovenian dialect treebank. The present version of the pipeline is designed to reduce the manual work. The pipeline has two modules – normalization and annotation. In the first stage, dialectal surface forms are normalized towards standard Slovenian through a sequence of corrected lexical replacements, deterministic phonological rules, Sloleks-based morphological validation, and a constrained GaMS residual corrector. The process preserves token order and alignment wherever possible and records substitutions that cannot be morphologically verified for later review. In the second stage, normalized sentences are parsed with the non-standard Slovenian CLASSLA-Stanza model, while SloBERTa identifies whatever could not be normalized and sends it to GaMS for a second check of the annotation. The resulting extended CoNLL-U representation retains the original dialect form alongside its normalized equivalent, Universal Dependencies annotation, dialect metadata, and audit information. The current output is intentionally silver-standard: native speakers and dialectologists will correct selected data into a gold subset, which will subsequently support evaluation and model fine-tuning. I will also show the web-platform developed based on user needs study held with corpora users.|| |
| Line 18: | Line 12: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''7 October 2019''' (NOTE: the seminar will start at 13:00!)|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Tomasz Stanisz''' (Institute of Nuclear Physics, Polish Academy of Sciences)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''What can a complex network say about a text?'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Complex networks, which have found application in the quantitative description of many different phenomena, have proven to be useful in research on natural language. The network formalism allows to study language from various points of view - a complex network may represent, for example, distances between given words in a text, semantic similarities, or grammatical relationships. One of the types of linguistic networks are word-adjacency networks, which describe mutual co-occurrences of words in texts. Although simple in construction, word-adjacency networks have a number of properties allowing for their practical use. The structure of such networks, expressed by appropriately defined quantities, reflects selected characteristics of language; applying machine learning methods to collections of those quantities may be used, for example, for authorship attribution.|| |
|
| Line 23: | Line 13: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''21 October 2019'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Piotr Przybyła''', '''Jakub Gąsior''' (Institute of Computer Science, Polish Academy of Sciences)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Two tasks of credibility assessment based on short text fragments: detecting bots on social media and extracting verifiable statements in political discussions'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The summary of the talk will be available shortly.|| |
||<style="border:0;padding-top:10px">Please see also [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/previous-e.html|the talks given in 2000–2015]] and [[http://zil.ipipan.waw.pl/seminar-archive|2015–2026]].|| |
| Line 28: | Line 15: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''18 November 2019'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Alexander Rosen''' (Charles University in Prague)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''The title of the talk will be available shortly'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk delivered in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The summary of the talk will be available shortly.|| |
{{{#!wiki comment |
| Line 33: | Line 17: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''21 November 2019'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Alexander Rosen''' (Charles University in Prague)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''The title of the talk will be available shortly'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk delivered in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The summary of the talk will be available shortly.|| |
||<style="border:0;padding-top:5px;padding-bottom:5px">'''17 November 2025''' '''(NOTE: the seminar will start at 16:00)'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Marzena Karpińska''' (Microsoft) || ||<style="border:0;padding-left:30px;padding-bottom:5px">[[http://zil.ipipan.waw.pl/seminarium-online|{{attachment:seminarium-archiwum/teams.png}}]] '''!OneRuler: testing multilingual language models on long contexts'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk in Polish}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">In this presentation, I will look at how well language models perform when extracting information from texts of up to 128,000 tokens (approximately 100,000 words) in 26 languages, including Polish. The results of the experiments show that as the length of the context increases, the differences between languages with large and small data resources also increase. Surprisingly, even minimal changes in the command (adding the possibility that the information does not exist) cause a significant decrease in effectiveness, especially with longer texts.|| |
| Line 38: | Line 22: |
| ||<style="border:0;padding-top:10px">Please see also [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/previous-e.html|the talks given in 2000–2015]] and [[http://zil.ipipan.waw.pl/seminar-archive|2015–2019]].|| | ||<style="border:0;padding-top:5px;padding-bottom:5px">'''11 March 2024'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Mateusz Krubiński''' (Charles University in Prague)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">[[http://zil.ipipan.waw.pl/seminarium-online|{{attachment:seminarium-archiwum/teams.png}}]] '''Talk title will be given shortly'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Talk summary will be made available soon.|| }}} |
Natural Language Processing Seminar 2026–2027
The NLP Seminar is organised by the Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences (ICS PAS). It takes place on (some) Mondays, usually at 10:15 am, often online – please use the link next to the presentation title. All recorded talks are available on YouTube. |
7 September 2026 |
Varvara Magomedova (University of Nova Gorica) |
Slovenian dialect research has produced a lot of literature, but not as many data sources. The lack of available syntactically annotated corpora limits research for those, who do not have access to native speakers. This talk presents the first phase of Veje – to become a Slovenian dialect treebank. The present version of the pipeline is designed to reduce the manual work. The pipeline has two modules – normalization and annotation. In the first stage, dialectal surface forms are normalized towards standard Slovenian through a sequence of corrected lexical replacements, deterministic phonological rules, Sloleks-based morphological validation, and a constrained GaMS residual corrector. The process preserves token order and alignment wherever possible and records substitutions that cannot be morphologically verified for later review. In the second stage, normalized sentences are parsed with the non-standard Slovenian CLASSLA-Stanza model, while SloBERTa identifies whatever could not be normalized and sends it to GaMS for a second check of the annotation. The resulting extended CoNLL-U representation retains the original dialect form alongside its normalized equivalent, Universal Dependencies annotation, dialect metadata, and audit information. The current output is intentionally silver-standard: native speakers and dialectologists will correct selected data into a gold subset, which will subsequently support evaluation and model fine-tuning. I will also show the web-platform developed based on user needs study held with corpora users. |
Please see also the talks given in 2000–2015 and 2015–2026. |


