Differences between revisions 500 and 739 (spanning 239 versions)
|
Size: 6729
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 2022–2023 = | = 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.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}}]]|| | ||<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">'''3 October 2022'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Sławomir Dadas''' (National Information Processing Institute)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">[[https://www.youtube.com/watch?v=TGwLeE1Y5X4|{{attachment:seminarium-archiwum/youtube.png}}]] '''[[attachment:seminarium-archiwum/2022-10-03.pdf|Our experience with training neural sentence encoders for the Polish language]]'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Representing sentences or short texts as dense vectors with a fixed number of dimensions is a common technique in tasks such as information retrieval, question answering, text clustering or plagiarism detection. A simple method to construct such representation is to aggregate vectors generated by a language model or extracted from word embeddings. However, higher quality representations can be obtained by fine-tuning a language model on a dataset of semantically similar sentence pairs. In this presentation, we will introduce methods for learning sentence encoders based on the Transformer architecture as well as our experiences with training such models for the Polish language. In addition, we will discuss approaches for building large datasets of paraphrases using publicly available corpora. We will also show a practical application of sentence encoders in a system developed for finding abusive clauses in consumer agreements.|| |
||<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">'''14 November 2022'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Łukasz Augustyniak''', '''Kamil Tagowski''', '''Albert Sawczyn''', '''Denis Janiak''', '''Roman Bartusiak''', '''Adrian Dominik Szymczak''', '''Arkadiusz Janz''', '''Piotr Szymański''', '''Marcin Wątroba''', '''Mikołaj Morzy''', '''Tomasz Jan Kajdanowicz''', '''Maciej Piasecki''' (Wrocław University of Science and Technology)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The availability of compute and data to train larger and larger language models increases the demand for robust methods of benchmarking the true progress of LM training. Recent years witnessed significant progress in standardized benchmarking for English. Benchmarks such as GLUE, SuperGLUE, or KILT have become a de facto standard tools to compare large language models. Following the trend to replicate GLUE for other languages, the KLEJ benchmark (''klej'' is the word for glue in Polish) has been released for Polish. In this paper, we evaluate the progress in benchmarking for low-resourced languages. We note that only a handful of languages have such comprehensive benchmarks. We also note the gap in the number of tasks being evaluated by benchmarks for resource-rich English/Chinese and the rest of the world. In this paper, we introduce LEPISZCZE (''lepiszcze'' is the Polish word for glew, the Middle English predecessor of glue), a new, comprehensive benchmark for Polish NLP with a large variety of tasks and high-quality operationalization of the benchmark. We design LEPISZCZE with flexibility in mind. Including new models, datasets, and tasks is as simple as possible while still offering data versioning and model tracking. In the first run of the benchmark, we test 13 experiments (task and dataset pairs) based on the five most recent LMs for Polish. We use five datasets from the Polish benchmark and add eight novel datasets. As the paper's main contribution, apart from LEPISZCZE, we provide insights and experiences learned while creating the benchmark for Polish as the blueprint to design similar benchmarks for other low-resourced languages.|| ||<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|2015–2020]].|| |
||<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 20: | Line 15: |
||<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 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. |
