# Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation

arXiv: https://arxiv.org/abs/1609.07730 · HTML: https://mlsanity.com/paper/1609.07730/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2016.

## Built on by (most cited first, 11 of 11)

- [A Survey of Mamba](https://mlsanity.com/paper/2408.01129/) (2024)
- [Structural Information Preserving for Graph-to-Text Generation](https://mlsanity.com/paper/2102.06749/) (2021)
- [R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents](https://mlsanity.com/paper/2303.00732/) (2023)
- [Lattention: Lattice-attention in ASR rescoring](https://mlsanity.com/paper/2111.10157/) (2021)
- [A comparative study of neural network techniques for automatic software vulnerability detection](https://mlsanity.com/paper/2104.14978/) (2021)
- [Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation](https://mlsanity.com/paper/2110.10261/) (2021)
- [LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud](https://mlsanity.com/paper/2309.17157/) (2023)
- [ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines](https://mlsanity.com/paper/2302.03851/) (2023)
- [Diverse Sign Language Translation](https://mlsanity.com/paper/2410.19586/) (2024)
- [Exploiting Word Semantics to Enrich Character Representations of Chinese Pre-trained Models](https://mlsanity.com/paper/2207.05928/) (2022)
- [Lattice-Based Pruning in Recurrent Neural Networks via Poset Modeling](https://mlsanity.com/paper/2502.16525/) (2025)

## Abstract (arXiv)

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.