Abstract
The University of Edinburgh participated in all six tracks: NLG, MT, and MT+NLG with both English and German as targeted languages. For the NLG track, we submitted a multilingual system based on the Content Selection and Planning model of Puduppully et al (2019). For the MT track, we submitted Transformer-based Neural Machine Translation models, where out-of-domain parallel data was augmented with in-domain data extracted from monolingual corpora. Our MT+NLG systems disregard the structured input data and instead rely exclusively on the source summaries.- Anthology ID:
- D19-5630
- Volume:
- Proceedings of the 3rd Workshop on Neural Generation and Translation
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong
- Venue:
- NGT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 268–272
- Language:
- URL:
- https://aclanthology.org/D19-5630
- DOI:
- 10.18653/v1/D19-5630
- Cite (ACL):
- Ratish Puduppully, Jonathan Mallinson, and Mirella Lapata. 2019. University of Edinburgh’s submission to the Document-level Generation and Translation Shared Task. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 268–272, Hong Kong. Association for Computational Linguistics.
- Cite (Informal):
- University of Edinburgh’s submission to the Document-level Generation and Translation Shared Task (Puduppully et al., NGT 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D19-5630.pdf
- Code
- ratishsp/data2text-table-plan-py