Zero-Resource Neural Machine Translation with Multi-Agent Communication Game

By Yun Chen, Yang Liu, Victor O. K. Li. 2018

49 citations recorded by the source corpus.

While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem for low-resource language pairs and domains. To tackle this problem, we propose an interactive multimodal framework for zero-resource neural machine translation. Instead of being passively exposed to large amounts of parallel corpora, our learners (implemented as encoder-decoder architecture) engage in cooperative image description games, and thus develop their own image captioning or neural machine translation model from the need to communicate in order to succeed at the game. Experimental results on the IAPR-TC12 and Multi30K datasets show that the proposed learning mechanism significantly improves over the state-of-the-art methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Orhan Firat
2. Graham Neubig
3. Ankur Bapna
4. Jiatao Gu
5. Kyunghyun Cho
6. Felix Stahlberg
7. Luke S. Zettlemoyer
8. Naveen Arivazhagan

In Computer Vision and Pattern Recognition

1. Orhan Firat
2. Ankur Bapna
3. Kyunghyun Cho
4. Graham Neubig
5. Jiatao Gu
6. Felix Stahlberg
7. Jianfei Cai
8. Naveen Arivazhagan

In Natural Language Processing

1. Orhan Firat
2. Ankur Bapna
3. Graham Neubig
4. Jiatao Gu
5. Kyunghyun Cho
6. Felix Stahlberg
7. Rico Sennrich
8. Philipp Koehn

In Reinforcement Learning

1. Jianfei Cai
2. Kyunghyun Cho
3. Victor O. K. Li
4. G. Wang
5. Z. Chen
6. Shafiq R. Joty
7. Jiatao Gu
8. Yonghui Wu

Citations in the corpus

• Meta-Learning for Low-Resource Neural Machine Translation (2018, background): “For instance, Cheng et al. (2016); Chen et al. (2017); Lee et al. (2017); Chen et al. (2018) investigate the use of a pivot to build a translation path be-tween two languages even without any directed resource.”
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, methodology): “The most effective approach has been to simply synthesize parallel data (Firat et al., 2016b; Chen et al., 2017, 2018b) and incorporate that into the training process.”
• Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations (2019, background): “For instance, there have been attempts to train a single-pair model with a pivot-language (Cheng et al., 2016; Chen et al., 2017) or a pivot-image (Lee et al., 2017; Chen et al., 2018).”
• Unpaired Image Captioning by Language Pivoting (2018, background): “The concept of using a pivot language as an intermediary language has been studied previously in machine translation (MT) to translate between a resourcerich language and a resource-scarce language [46, 42, 25, 6].”
• A Survey of Multilingual Neural Machine Translation (2019, background): “Hence, there has been a massive increase in work on MT systems that involve more than two languages (Dong et al., 2015; Firat et al., 2016a; Zoph and Knight, 2016; Cheng et al., 2017; Johnson et al., 2017; Chen et al., 2017, 2018b; Neu-big and Hu, 2018) etc .”