# Cross-lingual Inflection as a Data Augmentation Method for Parsing

arXiv: https://arxiv.org/abs/2205.09350 · HTML: https://mlsanity.com/paper/2205.09350/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 19 May 2022.

## Builds on (most cited first, 12 of 12)

- [Fully Character-Level Neural Machine Translation without Explicit Segmentation](https://mlsanity.com/paper/1610.03017/) (2016)
- [Applying the Transformer to Character-level Transduction](https://mlsanity.com/paper/2005.10213/) (2020)
- [UniMorph 2.0: Universal Morphology](https://mlsanity.com/paper/1810.11101/) (2018)
- [Stack-Pointer Networks for Dependency Parsing](https://mlsanity.com/paper/1805.01087/) (2018)
- [Viable Dependency Parsing as Sequence Labeling](https://mlsanity.com/paper/1902.10505/) (2019)
- [Many Languages, One Parser](https://mlsanity.com/paper/1602.01595/) (2016)
- [Bracketing Encodings for 2-Planar Dependency Parsing](https://mlsanity.com/paper/2011.00596/) (2020)
- [Hard Non-Monotonic Attention for Character-Level Transduction](https://mlsanity.com/paper/1808.10024/) (2018)
- [Marrying Universal Dependencies and Universal Morphology](https://mlsanity.com/paper/1810.06743/) (2018)
- [Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing](https://mlsanity.com/paper/2108.07556/) (2021)
- [Low-Resource Parsing with Crosslingual Contextualized Representations](https://mlsanity.com/paper/1909.08744/) (2019)
- [One model, two languages: training bilingual parsers with harmonized treebanks](https://mlsanity.com/paper/1507.08449/) (2015)

## Abstract (arXiv)

We propose a morphology-based method for low-resource (LR) dependency parsing. We train a morphological inflector for target LR languages, and apply it to related rich-resource (RR) treebanks to create cross-lingual (x-inflected) treebanks that resemble the target LR language. We use such inflected treebanks to train parsers in zero- (training on x-inflected treebanks) and few-shot (training on x-inflected and target language treebanks) setups. The results show that the method sometimes improves the baselines, but not consistently.