Zero-Resource Neural Machine Translation with Multi-Agent Communication Game
This addresses the problem of zero-resource translation for low-resource language pairs, offering a novel approach but is incremental in the broader context of NMT.
The paper tackles the data scarcity problem in neural machine translation for low-resource languages by proposing an interactive multimodal framework where learners engage in cooperative image description games to develop translation models without parallel corpora. Experimental results on IAPR-TC12 and Multi30K datasets show significant improvements over state-of-the-art methods.
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.