Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Isbister, Tim"'
Autor:
Norlund, Tobias, Isbister, Tim, Gyllensten, Amaru Cuba, Santos, Paul Dos, Petrelli, Danila, Ekgren, Ariel, Sahlgren, Magnus
This paper presents the hitherto largest pretraining dataset for the Scandinavian languages: the Scandinavian WEb (SWEb), comprising over one trillion tokens. The paper details the collection and processing pipeline, and introduces a novel model-base
Externí odkaz:
http://arxiv.org/abs/2410.04456
Autor:
Ekgren, Ariel, Gyllensten, Amaru Cuba, Stollenwerk, Felix, Öhman, Joey, Isbister, Tim, Gogoulou, Evangelia, Carlsson, Fredrik, Heiman, Alice, Casademont, Judit, Sahlgren, Magnus
This paper details the process of developing the first native large generative language model for the Nordic languages, GPT-SW3. We cover all parts of the development process, from data collection and processing, training configuration and instructio
Externí odkaz:
http://arxiv.org/abs/2305.12987
Autor:
Öhman, Joey, Verlinden, Severine, Ekgren, Ariel, Gyllensten, Amaru Cuba, Isbister, Tim, Gogoulou, Evangelia, Carlsson, Fredrik, Sahlgren, Magnus
Pre-training Large Language Models (LLMs) require massive amounts of text data, and the performance of the LLMs typically correlates with the scale and quality of the datasets. This means that it may be challenging to build LLMs for smaller languages
Externí odkaz:
http://arxiv.org/abs/2303.17183
Recent studies in zero-shot cross-lingual learning using multilingual models have falsified the previous hypothesis that shared vocabulary and joint pre-training are the keys to cross-lingual generalization. Inspired by this advancement, we introduce
Externí odkaz:
http://arxiv.org/abs/2109.07348
Most work in NLP makes the assumption that it is desirable to develop solutions in the native language in question. There is consequently a strong trend towards building native language models even for low-resource languages. This paper questions thi
Externí odkaz:
http://arxiv.org/abs/2104.10441
Autor:
Isbister, Tim, Sahlgren, Magnus
This paper presents the first Swedish evaluation benchmark for textual semantic similarity. The benchmark is compiled by simply running the English STS-B dataset through the Google machine translation API. This paper discusses potential problems with
Externí odkaz:
http://arxiv.org/abs/2009.03116
In this study, we examined the possibility to extract personality traits from a text. We created an extensive dataset by having experts annotate personality traits in a large number of texts from multiple online sources. From these annotated texts, w
Externí odkaz:
http://arxiv.org/abs/1910.09916
Hateful comments, swearwords and sometimes even death threats are becoming a reality for many people today in online environments. This is especially true for journalists, politicians, artists, and other public figures. This paper describes how hate
Externí odkaz:
http://arxiv.org/abs/1803.04757
Autor:
Isbister, Tim
This thesis explores whether it is possible to capture communication patterns from web-forums and detect anomalous user behaviour. Data from individuals on web-forums can be downloaded using web-crawlers, and tools as LIWC can make the data meaningfu
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-269189