|
Size: 4636
Comment:
|
Size: 6363
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 3: | Line 3: |
| = Natural Language Processing Seminar 2020–2021 = | = Natural Language Processing Seminar 2021–2022 = |
| 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, currently 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-bottom:10px">'''NOTE''': Due to restriction of admission to the Institute building, only staff and speakers (including external ones) may currently take part in the seminar. For all other participants the seminar will be broadcast on [[https://www.youtube.com/channel/UC5PEPpMqjAr7Pgdvq0wRn0w||YouTube]].|| | ||<style="border:0;padding-top:5px;padding-bottom:5px">'''4 October 2021'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Joanna Byszuk''' (Institute of Polish Language, Polish Academy of Sciences)|| ||<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.|| |
| Line 9: | Line 12: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''5 October 2020'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Piotr Rybak''', '''Robert Mroczkowski''', '''Janusz Tracz''' (ML Research at Allegro.pl), '''Ireneusz Gawlik''' (ML Research at Allegro.pl & AGH University of Science and Technology)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Review of BERT-based Models for Polish Language'''  {{attachment:seminarium-archiwum/icon-pl.gif|Delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">In recent years, a series of BERT-based models improved the performance of many natural language processing systems. During this talk, we will briefly introduce the BERT model as well as some of its variants. Next, we will focus on the available BERT-based models for Polish language and their results on the KLEJ benchmark. Finally, we will dive into the details of the new model developed in cooperation between ICS PAS and Allegro.|| |
||<style="border:0;padding-top:5px;padding-bottom:5px">'''18 October 2021'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Jan Kocoń''', '''Przemysław Kazienko''' (Wrocław University of Technology)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Personalized NLP'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">Many natural language processing tasks, such as classifying offensive, toxic, or emotional texts, are inherently subjective in nature. This is a major challenge, especially with regard to the annotation process. Humans tend to perceive textual content in their own individual way. Most current annotation procedures aim to achieve a high level of agreement in order to generate a high quality reference source. Existing machine learning methods commonly rely on agreed output values that are the same for all annotators. However, annotation guidelines for subjective content can limit annotators' decision-making freedom. Motivated by moderate annotation agreement on offensive and emotional content datasets, we hypothesize that a personalized approach should be introduced for such subjective tasks. We propose new deep learning architectures that take into account not only the content but also the characteristics of the individual. We propose different approaches for learning the representation and processing of data about text readers. Experiments were conducted on four datasets: Wikipedia discussion texts labeled with attack, aggression, and toxicity, and opinions annotated with ten numerical emotional categories. All of our models based on human biases and their representations significantly improve prediction quality in subjective tasks evaluated from an individual's perspective. Additionally, we have developed requirements for annotation, personalization, and content processing procedures to make our solutions human-centric.|| |
| Line 14: | Line 17: |
| ||<style="border:0;padding-top:5px;padding-bottom:5px">'''19 October 2020'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Inez Okulska''' (NASK National Research Institute)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Concise, robust, sparse? Algebraic transformations of word2vec embeddings versus precision of classification'''  {{attachment:seminarium-archiwum/icon-pl.gif|Talk delivered in Polish.}}|| ||<style="border:0;padding-left:30px;padding-bottom:15px">The talk summary will be available shortly.|| |
||<style="border:0;padding-top:5px;padding-bottom:5px">'''8 November 2021'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Ryszard Tuora''', '''Łukasz Kobyliński''' (Institute of Computer Science, Polish Academy of Sciences)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''Dependency Trees in Automatic Inflection of Multi Word Expressions in Polish'''  {{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">'''22 November 2021'''|| ||<style="border:0;padding-left:30px;padding-bottom:0px">'''Piotr Przybyła''' (Institute of Computer Science, Polish Academy of Sciences)|| ||<style="border:0;padding-left:30px;padding-bottom:5px">'''When classification accuracy is not enough: Explaining news credibility assessment and measuring users' reaction'''  {{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: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]].|| |
| Line 26: | Line 36: |
||<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]].|| |
Natural Language Processing Seminar 2021–2022
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, currently online – please use the link next to the presentation title. All recorded talks are available on YouTube. |
|
4 October 2021 |
Joanna Byszuk (Institute of Polish Language, Polish Academy of Sciences) |
Talk title will be available shortly |
Talk summary will be available shortly. |
18 October 2021 |
Jan Kocoń, Przemysław Kazienko (Wrocław University of Technology) |
Personalized NLP |
Many natural language processing tasks, such as classifying offensive, toxic, or emotional texts, are inherently subjective in nature. This is a major challenge, especially with regard to the annotation process. Humans tend to perceive textual content in their own individual way. Most current annotation procedures aim to achieve a high level of agreement in order to generate a high quality reference source. Existing machine learning methods commonly rely on agreed output values that are the same for all annotators. However, annotation guidelines for subjective content can limit annotators' decision-making freedom. Motivated by moderate annotation agreement on offensive and emotional content datasets, we hypothesize that a personalized approach should be introduced for such subjective tasks. We propose new deep learning architectures that take into account not only the content but also the characteristics of the individual. We propose different approaches for learning the representation and processing of data about text readers. Experiments were conducted on four datasets: Wikipedia discussion texts labeled with attack, aggression, and toxicity, and opinions annotated with ten numerical emotional categories. All of our models based on human biases and their representations significantly improve prediction quality in subjective tasks evaluated from an individual's perspective. Additionally, we have developed requirements for annotation, personalization, and content processing procedures to make our solutions human-centric. |
8 November 2021 |
Ryszard Tuora, Łukasz Kobyliński (Institute of Computer Science, Polish Academy of Sciences) |
Dependency Trees in Automatic Inflection of Multi Word Expressions in Polish |
Talk summary will be available shortly. |
22 November 2021 |
Piotr Przybyła (Institute of Computer Science, Polish Academy of Sciences) |
When classification accuracy is not enough: Explaining news credibility assessment and measuring users' reaction |
Talk summary will be available shortly. |
Please see also the talks given in 2000–2015 and 2015–2020. |
