Optimally Segmenting Inputs for NMT Shows Preference for Character-Level Processing

10/02/2018
by   Julia Kreutzer, et al.
0

Most modern neural machine translation (NMT) systems rely on presegmented inputs. Segmentation granularity importantly determines the input and output sequence lengths, hence the modeling depth, and source and target vocabularies, which in turn determine model size, computational costs of softmax normalization, and handling of out-of-vocabulary words. However, the current practice is to use static, heuristic-based segmentations that are fixed before NMT training. This begs the question whether the chosen segmentation is optimal for the translation task. To overcome suboptimal segmentation choices, we present an algorithm for dynamic segmentation based on the Adaptative Computation Time algorithm (Graves 2016), that is trainable end-to-end and driven by the NMT objective. In an evaluation on three translation tasks we found that, given the freedom to navigate between different segmentation levels, the model prefers to operate on (almost) character level, providing support for purely character-level NMT models from a novel angle.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset