|
Size: 834
Comment:
|
Size: 6899
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 3: | Line 3: |
| = Natural Language Processing Seminar 2016–2017 = | = Natural Language Processing Seminar 2023–2024 = |
| Line 5: | Line 5: |
| ||<style="border:0;padding:0">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). ||<style="border:0;padding-left:30px">[[seminarium-archiwum|{{attachment: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:10px">Please come back in October! And now see [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/previous-e.html|the talks given between 2000 and 2015]] and [[http://zil.ipipan.waw.pl/seminar|2015-16]]. | ||<style="border:0;padding-top:5px;padding-bottom:5px">'''9 October 2023'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Agnieszka Mikołajczyk-Bareła''', '''Wojciech Janowski''' (!VoiceLab), '''Piotr Pęzik''' (University of Łódź / !VoiceLab), '''Filip Żarnecki''', '''Alicja Golisowicz''' (!VoiceLab)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">[[http://zil.ipipan.waw.pl/seminarium-online|{{attachment:seminarium-archiwum/teams.png}}]] '''[[attachment:seminarium-archiwum/2023-10-09.pdf|TRURL.AI: Fine-tuning large language models on multilingual instruction datasets]]'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">This talk will summarize our recent work on fine-tuning a large generative language model on bilingual instruction datasets, which resulted in the release of an open version of Trurl (trurl.ai). The motivation behind creating this model was to improve the performance of the original Llama 2 7B- and 13B-parameter models (Touvron et al. 2023), from which it was derived in a number of areas such as information extraction from customer-agent interactions and data labeling with a special focus on processing texts and instructions written in Polish. We discuss the process of optimizing the instruction datasets and the effect of the fine-tuning process on a number of selected downstream tasks.|| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''16 October 2023'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Konrad Wojtasik''', '''Vadim Shishkin''', '''Kacper Wołowiec''', '''Arkadiusz Janz''', '''Maciej Piasecki''' (Wrocław University of Science and Technology)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">[[http://zil.ipipan.waw.pl/seminarium-online|{{attachment:seminarium-archiwum/teams.png}}]] '''Evaluation of information retrieval models in zero-shot settings on different documents domains'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk delivered in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Information Retrieval over large collections of documents is an extremely important research direction in the field of natural language processing. It is a key component in question-answering systems, where the answering model often relies on information contained in a database with up-to-date knowledge. This not only allows for updating the knowledge upon which the system responds to user queries but also limits its hallucinations. Currently, information retrieval models are neural networks and require significant training resources. For many years, lexical matching methods like BM25 outperformed trained neural models in Open Domain setting, but current architectures and extensive datasets allow surpassing lexical solutions. In the presentation, I will introduce available datasets for the evaluation and training of modern information retrieval architectures in document collections from various domains, as well as future development directions.|| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''30 October 2023'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Agnieszka Faleńska''' (University of Stuttgart)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">[[http://zil.ipipan.waw.pl/seminarium-online|{{attachment:seminarium-archiwum/teams.png}}]] '''Steps towards Bias-Aware NLP Systems'''  {{attachment:seminarium-archiwum/icon-en.gif|Talk in English.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The summary will be available soon.|| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''13 November 2023'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Piotr Rybak''' (Institute of Computer Science, Polish Academy of Sciences)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Advancing Polish Question Answering: Datasets and Models'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The summary will be available soon.|| ||<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|2015–2023]].|| {{{#!wiki comment ||<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 2023–2024
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. |
|
9 October 2023 |
Agnieszka Mikołajczyk-Bareła, Wojciech Janowski (VoiceLab), Piotr Pęzik (University of Łódź / VoiceLab), Filip Żarnecki, Alicja Golisowicz (VoiceLab) |
|
This talk will summarize our recent work on fine-tuning a large generative language model on bilingual instruction datasets, which resulted in the release of an open version of Trurl (trurl.ai). The motivation behind creating this model was to improve the performance of the original Llama 2 7B- and 13B-parameter models (Touvron et al. 2023), from which it was derived in a number of areas such as information extraction from customer-agent interactions and data labeling with a special focus on processing texts and instructions written in Polish. We discuss the process of optimizing the instruction datasets and the effect of the fine-tuning process on a number of selected downstream tasks. |
16 October 2023 |
Konrad Wojtasik, Vadim Shishkin, Kacper Wołowiec, Arkadiusz Janz, Maciej Piasecki (Wrocław University of Science and Technology) |
|
Information Retrieval over large collections of documents is an extremely important research direction in the field of natural language processing. It is a key component in question-answering systems, where the answering model often relies on information contained in a database with up-to-date knowledge. This not only allows for updating the knowledge upon which the system responds to user queries but also limits its hallucinations. Currently, information retrieval models are neural networks and require significant training resources. For many years, lexical matching methods like BM25 outperformed trained neural models in Open Domain setting, but current architectures and extensive datasets allow surpassing lexical solutions. In the presentation, I will introduce available datasets for the evaluation and training of modern information retrieval architectures in document collections from various domains, as well as future development directions. |
30 October 2023 |
Agnieszka Faleńska (University of Stuttgart) |
|
The summary will be available soon. |
13 November 2023 |
Piotr Rybak (Institute of Computer Science, Polish Academy of Sciences) |
Advancing Polish Question Answering: Datasets and Models |
The summary will be available soon. |
Please see also the talks given in 2000–2015 and 2015–2023. |