What do Neural Machine Translation Models Learn about Morphology?
This provides insights into the inner workings of neural MT models for researchers and practitioners, though it is incremental as it builds on existing analysis methods.
The paper tackled the problem of understanding what neural machine translation models learn about morphology by analyzing their representations through extrinsic tagging tasks, finding that they capture morphological information effectively, with character-based representations and deeper layers performing better.
Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training process. In this work, we analyze the representations learned by neural MT models at various levels of granularity and empirically evaluate the quality of the representations for learning morphology through extrinsic part-of-speech and morphological tagging tasks. We conduct a thorough investigation along several parameters: word-based vs. character-based representations, depth of the encoding layer, the identity of the target language, and encoder vs. decoder representations. Our data-driven, quantitative evaluation sheds light on important aspects in the neural MT system and its ability to capture word structure.