Beyond Weight Tying: Learning Joint Input-Output Embeddings for Neural Machine Translation

Abstract

Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we investigate other forms of sharing in between no sharing and hard equality of parameters. In particular, we propose a structure-aware output layer which captures the semantic structure of the output space of words within a joint input-output embedding. The model is a generalized form of weight tying which shares parameters but allows learning a more flexible relationship with input word embeddings and allows the effective capacity of the output layer to be controlled. In addition, the model shares weights across output classifiers and translation contexts which allows it to better leverage prior knowledge about them. Our evaluation on English-to-Finnish and English-to-German datasets shows the effectiveness of the method against strong encoder-decoder baselines trained with or without weight tying.

arXiv commentTo appear at WMT 2018

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Convolutional Sequence to Sequence Learning
• Effective Approaches to Attention-based Neural Machine Translation
• Character-based Neural Machine Translation
• Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
• Learning Deep Latent Spaces for Multi-Label Classification
• GILE: A Generalized Input-Label Embedding for Text Classification