# Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization

arXiv: https://arxiv.org/abs/1811.01100 · HTML: https://mlsanity.com/paper/1811.01100/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [Controlling Conditional Language Models without Catastrophic Forgetting](https://mlsanity.com/paper/2112.00791/) (2021)
- [A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints](https://mlsanity.com/paper/2312.03905/) (2023)
- [Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT](https://mlsanity.com/paper/2109.01396/) (2021)
- [Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing](https://mlsanity.com/paper/2203.04665/) (2022)
- [Continuous Learning in Neural Machine Translation using Bilingual Dictionaries](https://mlsanity.com/paper/2102.06558/) (2021)
- [ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2210.03999/) (2022)
- [Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation](https://mlsanity.com/paper/2107.13077/) (2021)
- [Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering](https://mlsanity.com/paper/2305.04522/) (2023)
- [Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting](https://mlsanity.com/paper/2312.04807/) (2023)

## Abstract (arXiv)

Although neural machine translation has made significant progress recently, how to integrate multiple overlapping, arbitrary prior knowledge sources remains a challenge. In this work, we propose to use posterior regularization to provide a general framework for integrating prior knowledge into neural machine translation. We represent prior knowledge sources as features in a log-linear model, which guides the learning process of the neural translation model. Experiments on Chinese-English translation show that our approach leads to significant improvements.