Abstract
Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challenges in efficiently learning word representations in the face of paucity of data. In this paper, we propose Soft Decoupled Encoding (SDE), a multilingual lexicon encoding framework specifically designed to share lexical-level information intelligently without requiring heuristic preprocessing such as pre-segmenting the data. SDE represents a word by its spelling through a character encoding, and its semantic meaning through a latent embedding space shared by all languages. Experiments on a standard dataset of four low-resource languages show consistent improvements over strong multilingual NMT baselines, with gains of up to 2 BLEU on one of the tested languages, achieving the new state-of-the-art on all four language pairs.
Original language | English |
---|---|
Title of host publication | International Conference on Learning Representations 2019 |
Editors | Alexander Rush |
Place of Publication | La Jolla CA USA |
Publisher | International Conference on Learning Representations (ICLR) |
Number of pages | 13 |
ISBN (Print) | 9783800743629 |
Publication status | Published - 2019 |
Event | International Conference on Learning Representations 2019 - Ernest N. Morial Convention Center, New Orleans, United States of America Duration: 6 May 2019 → 9 May 2019 Conference number: 7th https://iclr.cc/Conferences/2019 https://openreview.net/group?id=ICLR.cc/2019/Conference (Proceedings) |
Conference
Conference | International Conference on Learning Representations 2019 |
---|---|
Abbreviated title | ICLR 2019 |
Country/Territory | United States of America |
City | New Orleans |
Period | 6/05/19 → 9/05/19 |
Other | The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics. |
Internet address |