Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning
Proceedings of the Northern Lights Deep Learning Workshop · 2022
DOI: 10.7557/18.6231 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Northern Lights Deep Learning Workshop, 2022. Verfasst von Tosin Adewumi und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Building open-domain conversational systems (or chatbots) that produce convincing responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based models for the generation of natural language dialogue have demonstrated impressive performance in simulating human-like, single-turn conversations in English. This work investigates, by an empirical study, the potential for transfer learning of such models to Swedish language. DialoGPT, an English language pre-trained model, is adapted by training on three different Swedish language conversational datasets obtained from publicly available sources. Perplexity score (an automated intrinsic language model metric) and surveys by human evaluation were used to assess the performances of the fine-tuned models, with results that indicate that the capacity for transfer learning can be exploited with considerable success. Human evaluators asked to score the simulated dialogue judged over 57% of the chatbot responses to be human-like for the model trained on the largest (Swedish) dataset. We provide the demos and model checkpoints of our English and Swedish chatbots on the HuggingFace platform for public use.
Zitieren
APA
Adewumi, T., Brännvall, R., Abid, N., Pahlavan, M., Sabah, S., Liwicki, F., & Liwicki, M. (2022). Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning. Proceedings of the Northern Lights Deep Learning Workshop. https://doi.org/10.7557/18.6231
Vancouver
Adewumi T, Brännvall R, Abid N, Pahlavan M, Sabah S, Liwicki F, et al. Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning. Proceedings of the Northern Lights Deep Learning Workshop. 2022. doi:10.7557/18.6231
BibTeX
@article{Adewumi2022,
author = {Adewumi, Tosin and Brännvall, Rickard and Abid, Nosheen and Pahlavan, Maryam and Sabah, Sana and Liwicki, Foteini and Liwicki, Marcus},
title = {Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning},
journal = {Proceedings of the Northern Lights Deep Learning Workshop},
year = {2022},
doi = {10.7557/18.6231}
}
EUVIMED