# Neural Machine Translation with Explicit Phrase Alignment

arXiv: https://arxiv.org/abs/1911.11520 · HTML: https://mlsanity.com/paper/1911.11520/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [CTC Alignments Improve Autoregressive Translation](https://mlsanity.com/paper/2210.05200/) (2022)
- [GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation](https://mlsanity.com/paper/2207.14467/) (2022)
- [Integrating Vectorized Lexical Constraints for Neural Machine Translation](https://mlsanity.com/paper/2203.12210/) (2022)
- [On-the-Fly Fusion of Large Language Models and Machine Translation](https://mlsanity.com/paper/2311.08306/) (2023)
- [InFillmore: Frame-Guided Language Generation with Bidirectional Context](https://mlsanity.com/paper/2103.04941/) (2021)
- [GCRE-GPT: A Generative Model for Comparative Relation Extraction](https://mlsanity.com/paper/2303.08601/) (2023)
- [N-Gram Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2301.12866/) (2023)
- [A Template-based Method for Constrained Neural Machine Translation](https://mlsanity.com/paper/2205.11255/) (2022)
- [Perplexity from PLM Is Unreliable for Evaluating Text Quality](https://mlsanity.com/paper/2210.05892/) (2022)
- [Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting](https://mlsanity.com/paper/2312.04807/) (2023)

## Abstract (arXiv)

While neural machine translation (NMT) has achieved state-of-the-art translation performance, it is unable to capture the alignment between the input and output during the translation process. The lack of alignment in NMT models leads to three problems: it is hard to (1) interpret the translation process, (2) impose lexical constraints, and (3) impose structural constraints. To alleviate these problems, we propose to introduce explicit phrase alignment into the translation process of arbitrary NMT models. The key idea is to build a search space similar to that of phrase-based statistical machine translation for NMT where phrase alignment is readily available. We design a new decoding algorithm that can easily impose lexical and structural constraints. Experiments show that our approach makes the translation process of NMT more interpretable without sacrificing translation quality. In addition, our approach achieves significant improvements in lexically and structurally constrained translation tasks.