conftrace_

2019 EMNLP EMNLP 2019

LORIA / Lorraine University at Multilingual Surface Realisation 2019

Abstract

AbstractThis paper presents the LORIA / Lorraine University submission at the Multilingual Surface Realisation shared task 2019 for the shallow track. We outline our approach and evaluate it on 11 languages covered by the shared task. We provide a separate evaluation of each component of our pipeline, concluding on some difficulties and suggesting directions for future work.

🐣 Hot Topic Early Bird - multilingual processing

Authors

Anastasia Shimorina, Claire Gardent

Topics

Natural Language Processing > Generation > Text Generation Natural Language Processing > Resources & Methods > Multilingual NLP

Keywords

multilingual nlp text generation multilingual processing surface realization pipeline approach pipeline architecture language coverage surface realisation

More from EMNLP 2019

All EMNLP 2019 papers →

The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization

Improving Language Generation from Feature-Rich Tree-Structured Data with Relational Graph Convolutional Encoders

The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization

Back-Translation as Strategy to Tackle the Lack of Corpus in Natural Language Generation from Semantic Representations

Structure Learning for Neural Module Networks

Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task