Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation

TL;DR

This paper introduces a novel lattice-based RNN encoder for neural machine translation that effectively handles multiple tokenizations and reduces error propagation, improving translation quality for languages like Chinese.

Contribution

The paper proposes a new RNN encoder that processes word lattices, enabling more flexible and error-resilient input modeling in NMT systems for tokenization-challenged languages.

Findings

Outperforms standard encoders in Chinese-English translation

Reduces impact of tokenization errors

Enhances input sentence embedding flexibility

Abstract

Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters (e.g., Chinese) where input sentences have to be tokenized first, conventional NMT is confronted with two issues: 1) it is difficult to find an optimal tokenization granularity for source sentence modelling, and 2) errors in 1-best tokenizations may propagate to the encoder of NMT. To handle these issues, we propose word-lattice based Recurrent Neural Network (RNN) encoders for NMT, which generalize the standard RNN to word lattice topology. The proposed encoders take as input a word lattice that compactly encodes multiple tokenizations, and learn to generate new hidden states from arbitrarily many inputs and hidden states in preceding time steps. As such, the word-lattice based encoders not only alleviate the negative impact of tokenization errors but also are more expressive and flexible to embed input sentences. Experiment results on Chinese-English translation demonstrate the superiorities of the proposed encoders over the conventional encoder.