# Translating from Morphologically Complex Languages: A Paraphrase-Based Approach

arXiv: https://arxiv.org/abs/2109.13724 · HTML: https://mlsanity.com/paper/2109.13724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 34 references that are in the map.
- First posted on arXiv 27 Sep 2021.

## Builds on (most cited first, 1 of 1)

- [Improved statistical machine translation using monolingual paraphrases](https://mlsanity.com/paper/2109.15119/) (2021)

## Abstract (arXiv)

We propose a novel approach to translating from a morphologically complex language. Unlike previous research, which has targeted word inflections and concatenations, we focus on the pairwise relationship between morphologically related words, which we treat as potential paraphrases and handle using paraphrasing techniques at the word, phrase, and sentence level. An important advantage of this framework is that it can cope with derivational morphology, which has so far remained largely beyond the capabilities of statistical machine translation systems. Our experiments translating from Malay, whose morphology is mostly derivational, into English show significant improvements over rivaling approaches based on five automatic evaluation measures (for 320,000 sentence pairs; 9.5 million English word tokens).