Skip to content
conftrace_
2019 EMNLP EMNLP 2019

SYSTRAN @ WNGT 2019: DGT Task

Abstract

AbstractThis paper describes SYSTRAN participation to the Document-level Generation and Trans- lation (DGT) Shared Task of the 3rd Workshop on Neural Generation and Translation (WNGT 2019). We participate for the first time using a Transformer network enhanced with modified input embeddings and optimising an additional objective function that considers content selection. The network takes in structured data of basketball games and outputs a summary of the game in natural language.

🐣 Hot Topic Early Bird - structured data

Authors

Li Gong, Josep Crego, Jean Senellart

Topics

Deep Learning > Architectures > Transformers Deep Learning > Models > Generative Models

Keywords

neural machine translation transformer network structured data content selection document generation
Download PDF

More from EMNLP 2019

All EMNLP 2019 papers →
Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation
Transformer and seq2seq model for Paraphrase Generation
Monash University’s Submissions to the WNGT 2019 Document Translation Task
University of Edinburgh’s submission to the Document-level Generation and Translation Shared Task
Naver Labs Europe’s Systems for the Document-Level Generation and Translation Task at WNGT 2019
From Research to Production and Back: Ludicrously Fast Neural Machine Translation