Abstract
Publications home
Naver Labs Europe’s systems for the document-level generation and translation task at WNGT 2019
at
| Fahimeh Saleh, Alexandre Berard, Ioan Calapodescu, Laurent Besacier |
| Workshop on Neural Generation and Translation (WNGT), EMNLP, Hong Kong, China, 4 November, 2019 |
@article{saleh2019naver,
title={Naver Labs Europe's Systems for the Document-Level Generation and Translation Task at WNGT 2019},
author={Saleh, Fahimeh and B{\'e}rard, Alexandre and Calapodescu, Ioan and Besacier, Laurent},
journal={arXiv preprint arXiv:1910.14539},
year={2019}
}Recently, neural models led to significant improvements in both machine translation (MT) and natural language generation (NLG) tasks.
However, generation of long descriptive summaries conditioned on structured data remains an open challenge. Likewise, MT that goes beyond sentence-level context is still an open issue (e.g., document-level MT or MT with metadata). To address these challenges, we propose to leverage data from both tasks and do transfer learning between MT, NLG, and MT with access to metadata. First, we focus on training a document-based MT system with the DGT parallel data. Then, we augment this MT model to obtain a “Data + Text to Text” MT model. Finally, we remove the text part of the input to obtain a pure NLG system, able to translate metadata to full documents. This end-to-end NLG approach, without data selection and planning, outperforms the previous state of the art on the Rotowire NLG dataset.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.