Differences between revisions 186 and 739 (spanning 553 versions)
|
Size: 6494
Comment:
|
← Revision 739 as of 2025-09-10 20:03:00 ⇥
Size: 4807
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 3: | Line 3: |
| = Natural Language Processing Seminar 2018–2019 = | = Natural Language Processing Seminar 2025–2026 = |
| 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 will restart in October and will take 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">'''1 October 2018'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Janusz S. Bień''' (University of Warsaw – prof. emeritus)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">[[https://www.youtube.com/watch?v=mOYzwpjTAf4|{{attachment:seminarium-archiwum/youtube.png}}]] '''[[attachment:seminarium-archiwum/2018-10-01.pdf|Electronic indexes to lexicographical resources]]'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">We will focus on the indexes to lexicographical resources available online in !DjVu format. Such indexes can be browsed, searched, modified and created with the djview4poliqarp open source program; the origins and the history of the program will be briefly presented. Originally the index support was added to the program to handle the list of entries in the 19th century Linde's dictionary, but can be used conveniently also for other resources, as will be demonstrated on selected examples. In particular some new features, introduced to the program in the last months, will be presented publicly for the first time.|| |
||<style="border:0;padding-top:5px;padding-bottom:5px">'''15 September 2025'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Louis Esteve''' (Universite Paris-Saclay) || ||<style="border:0;padding-left:30px;padding-bottom:5px">[[https://zil.ipipan.waw.pl/seminarium-online|{{attachment:seminarium-archiwum/teams.png}}]] '''Diversity and dataset size – a quantitative perspective'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The field of Natural Language Processing (NLP) studies the abilities of computer systems to process and generate natural language, and has received increasing attention from the general population since the democratisation of generative and conversational models. However, behind the scenes, state-of-the-art NLP models are trained on ever-larger datasets, reaching trillions of tokens. It may be argued that the creation and use of such immense datasets is motivated by the idea that 'the larger the dataset, the more diverse it is', and that in turn 'if the training set is more diverse, it shall yield better models'. However, these statements thus far remain intuitions and need to be properly tested. To this end, this presentation will tackle methods and caveats of formal diversity quantification including limitations of the literature, a preliminary discussion on the link between diversity and dataset size, as well as their impact on downstream applications.|| |
| Line 12: | Line 12: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''15 October 2018'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Wojciech Jaworski, Szymon Rutkowski''' (University of Warsaw)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''A multilayer rule based model of Polish inflection'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The presentation will be devoted to the multilayer model of Polish inflection. The model has been developed on the basis of Grammatical Dictionary of Polish; it does not use the concept of a inflexion paradigm. The model consists of three layers of hand-made rules: "orthographic-phonetic layer" converting a segment to representation reflecting morphological patterns of the language, "analytic layer" generating lemma and determining affix and "interpretation layer" giving a morphosyntactic interpretation based on detected affixes. The model provides knowledge about the language to a morphological analyzer supplemented with the function of guessing lemmas and morphosyntactic interpretations for non-dictionary forms (guesser). The second use of the model is generation of word forms based on lemma and morphosyntactic interpretation. The presentation will also cover the issue of disambiguation of the results provided by the morphological analyzer. The demo version of the program is available on the Internet.|| |
||<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|2015–2025]].|| |
| Line 17: | Line 14: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''29 October 2018'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Jakub Waszczuk'''|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Talk title will be available shortly'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Talk summary will be available shortly.|| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''5 November 2018'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Jakub Kozakoszczak''' (Faculty of Modern Languages, University of Warsaw / Heinrich-Heine-Universität Düsseldorf)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Talk title will be available shortly'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Talk summary will be available shortly.|| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''19 November 2018'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Daniel Zeman''' (Institute of Formal and Applied Linguistics, Charles University, Czech Republic)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Talk title will be available shortly'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk delivered in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Talk summary will be available shortly.|| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''3 December 2018'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Ekaterina Lapshinova-Koltunski''' (Saarland University)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Analysis and Annotation of Coreference for Contrastive Linguistics and Translation Studies'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk delivered in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">In this talk, I will report on the ongoing work on coreference analysis in a multilingual context. I will present two approaches in the analysis of coreference and coreference-related phenomena: (1) top-down or theory-driven: here we start from some linguistic knowledge derived from the existing frameworks, define linguistic categories to analyse and create an annotated corpus that can be used either for further linguistic analysis or as training data for NLP applications; (2) bottom-up or data-driven: in this case, we start from a set of features of shallow character that we believe are discourse-related. We extract these structures from a huge amount of data and analyse them from a linguistic point of view trying to describe and explain the observed phenomena from the point of view of existing theories and grammars.|| |
{{{#!wiki comment |
| Line 38: | Line 17: |
| ||<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|2015–2018]].|| | ||<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.|| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''2 April 2020'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Stan Matwin''' (Dalhousie University)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Efficient training of word embeddings with a focus on negative examples'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}} {{attachment:seminarium-archiwum/icon-en.gif|Slides in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">This presentation is based on our [[https://pdfs.semanticscholar.org/1f50/db5786913b43f9668f997fc4c97d9cd18730.pdf|AAAI 2018]] and [[https://aaai.org/ojs/index.php/AAAI/article/view/4683|AAAI 2019]] papers on English word embeddings. In particular, we examine the notion of “negative examples”, the unobserved or insignificant word-context co-occurrences, in spectral methods. we provide a new formulation for the word embedding problem by proposing a new intuitive objective function that perfectly justifies the use of negative examples. With the goal of efficient learning of embeddings, we propose a kernel similarity measure for the latent space that can effectively calculate the similarities in high dimensions. Moreover, we propose an approximate alternative to our algorithm using a modified Vantage Point tree and reduce the computational complexity of the algorithm with respect to the number of words in the vocabulary. We have trained various word embedding algorithms on articles of Wikipedia with 2.3 billion tokens and show that our method outperforms the state-of-the-art in most word similarity tasks by a good margin. We will round up our discussion with some general thought s about the use of embeddings in modern NLP.|| }}} |
Natural Language Processing Seminar 2025–2026
The NLP Seminar is organised by the Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences (ICS PAS). It will restart in October and will take 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. |
|
15 September 2025 |
Louis Esteve (Universite Paris-Saclay) |
|
The field of Natural Language Processing (NLP) studies the abilities of computer systems to process and generate natural language, and has received increasing attention from the general population since the democratisation of generative and conversational models. However, behind the scenes, state-of-the-art NLP models are trained on ever-larger datasets, reaching trillions of tokens. It may be argued that the creation and use of such immense datasets is motivated by the idea that 'the larger the dataset, the more diverse it is', and that in turn 'if the training set is more diverse, it shall yield better models'. However, these statements thus far remain intuitions and need to be properly tested. To this end, this presentation will tackle methods and caveats of formal diversity quantification including limitations of the literature, a preliminary discussion on the link between diversity and dataset size, as well as their impact on downstream applications. |
Please see also the talks given in 2000–2015 and 2015–2025. |
