Results 261 to 270 of about 52,931 (300)

SAGA: Collaborative Storytelling with GPT-3

Companion Publication of the 2021 Conference on Computer Supported Cooperative Work and Social Computing, 2021
When friends live across different time zones, have incompatible work schedules, or have different levels of access to technology, synchronous communication becomes infeasible. To address this challenge, we developed a web application that allows friends to asynchronously collaborate creatively.
Hanieh Shakeri, Carman Neustaedter, Steve DiPaola   +2 more
openaire   +1 more source

BERT, GPT-3, Timnit Gebru et nous

Sociologie et sociétés, 2023
Le déploiement aujourd’hui de modèles sémantiques automatisés tels le BERT de Google ou le GPT-3 d’OpenAI se montre comme un remarquable défi pour l’inscription de l’herméneutique au coeur même du projet des sciences sociales. L’intelligence artificielle est bel et bien à la conquête du langage. Cela implique d’abord qu’il faille prendre au sérieux les
Roberge, Jonathan, LeBrun, Tom
openaire   +3 more sources

Is GPT-3 a Good Data Annotator?

2022
GPT-3 (Generative Pre-trained Transformer 3) is a large-scale autoregressive language model developed by OpenAI, which has demonstrated impressive few-shot performance on a wide range of natural language processing (NLP) tasks. Hence, an intuitive application is to use it for data annotation. In this paper, we investigate whether GPT-3 can be used as a
Ding, Bosheng, Qin, Chengwei, Liu, Linlin, Bing, Lidong, Joty, Shafiq, Li, Boyang   +5 more
openaire   +1 more source

Text Summarization Quality Detection Based on GPT-3

Applied and Computational Engineering, 2023
To summarize lengthy text in a concise and accurate manner is called text summarization. With the increasing amount of information available, text summarization has become increasingly important in information retrieval, knowledge management, and sentiment analysis.
Sihan Qi, Honghao Zhang
openaire   +1 more source

Mono- and Multilingual GPT-3 Models for Hungarian

2023
In recent years, the growth in size of Transformer-based language models has accelerated significantly. Global technology companies are training larger and larger models that require enormous resources and training data. With these experiments, they aim to demonstrate that sufficiently large models with abundant training data can solve any natural ...
Yang, Zijian Győző, Laki, László János, Váradi, Tamás, Prószéky, Gábor   +3 more
openaire   +2 more sources

Experiments On GPT-3 Assisted Process Model Development

ECMS 2023 Proceedings edited by Enrico Vicario, Romeo Bandinelli, Virginia Fani, Michele Mastroianni, 2023
Computer assisted process model development from textual descriptions is still an open research question. Advantages of such a technology lie in shorter development times and possibly a more concise interpretation of the narrative input. A solution to this problem necessarily relies on methods from formal modeling and linguistics.
Carlo Simon, Stefan Haag, Lara Zakfeld
openaire   +1 more source

Riassumere testi giuridici con GPT-3

2023
In questa presentazione descriviamo sinteticamente una sperimentazione di summarization di testi giuridici effettuata con GPT-3 (Generative Pre-trained Transformer 3). Gli autori (ricercatori di informatica giuridica e di Natural Language Processing) hanno realizzato l'esperimento su un set eterogeneo di atti amministrativi e di norme di vario livello.
Andrea Bolioli*, Manola Cherubini, Francesco Romano, **Nazareno De Francesco   +3 more
openaire   +1 more source

Innovative Content Generation: Leveraging GPT-3 Language Capabilities

Journal of Innovative Technology Convergence, 2023
This study explores the utilization of OpenAI's GPT-3 in innovative content generation, leveraging its unparalleled language capabilities. GPT-3 represents a milestone in AI development, building upon earlier models like BERT and OpenAI's GPT series, propelled by the transformer architecture.
Kenette Roeven Saylo, Monalie Saylo
openaire   +1 more source

Brilliance Bias in GPT-3

2022 IEEE Global Humanitarian Technology Conference (GHTC), 2022
Juliana Shihadeh, Margareta Ackerman, Ashley Troske, Nicole Lawson, Edith Gonzalez   +4 more
openaire   +1 more source

Uporaba alata GPT-3 u obrazovanju

2023
Tema ovog završnog rada izrada je web-aplikacije koja će omogućiti razgovor (chat ili interaktivno) s osobama pomoću alata umjetne inteligencije. Osobe su ostvarene korištenjem aplikacijskog programskog sučelja OpenAI-a za upotrebu GPT-3.5 modela koji generira odgovore osobe na temelju konteksta razgovora.
openaire   +1 more source