Nothing Special   »   [go: up one dir, main page]

Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate (WebNLG 2023)

Michela Lorandi, Anya Belz


Abstract
LLMs are great at tasks involving English which dominates in their training data. We explore their ability to address tasks involving languages that are severely under-represented in their training data. More specifically, we do this in the context of data-to-text generation for Irish, Maltese, Welsh and Breton. During the prompt-engineering phase we tested GPT-3.5 and~4 with a range of prompt types and formats on a small sample of example input/output pairs. We then fully evaluated the two most promising prompts in two scenarios: (i) direct generation into the under-resourced languages, and (ii) generation into English followed by translation into the under-resourced languages. We find that few-shot prompting works better for direct generation into under-resourced languages, but that the difference disappears when pivoting via English. The few-shot + translation system variants were submitted to the WebNLG 2023 shared task where they outperformed all other systems by substantial margins in all languages on all automatic metrics. We conclude that good performance can be achieved with state-of-the-art LLMs out-of-the box for under-resourced languages. However, best results (for Welsh) of BLEU 25.12, ChrF++ 0.55, and TER 0.64 are well below the lowest ranked English system at WebNLG’20 with BLEU 0.391, ChrF++ 0.579, and TER 0.564.
Anthology ID:
2023.mmnlg-1.9
Volume:
Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023)
Month:
September
Year:
2023
Address:
Prague, Czech Republic
Editors:
Albert Gatt, Claire Gardent, Liam Cripwell, Anya Belz, Claudia Borg, Aykut Erdem, Erkut Erdem
Venues:
MMNLG | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
80–86
Language:
URL:
https://aclanthology.org/2023.mmnlg-1.9
DOI:
Bibkey:
Cite (ACL):
Michela Lorandi and Anya Belz. 2023. Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate (WebNLG 2023). In Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023), pages 80–86, Prague, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate (WebNLG 2023) (Lorandi & Belz, MMNLG-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.mmnlg-1.9.pdf