Cross-lingual Inflection as a Data Augmentation Method for Parsing
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 28 references that are in the map. First posted on arXiv 19 May 2022.
Builds on
12 of 28 references.
References · 12
- 2016Fully Character-Level Neural Machine Translation without Explicit Segmentationcited by 55
- 2020Applying the Transformer to Character-level Transductioncited by 43
- 2018UniMorph 2.0: Universal Morphologycited by 40
- 2018Stack-Pointer Networks for Dependency Parsingcited by 36
- 2019Viable Dependency Parsing as Sequence Labelingcited by 34
- 2016Many Languages, One Parsercited by 26
- 2020Bracketing Encodings for 2-Planar Dependency Parsingcited by 15
- 2018Hard Non-Monotonic Attention for Character-Level Transductioncited by 12
- 2018Marrying Universal Dependencies and Universal Morphologycited by 11
- 2021Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsingcited by 7
- 2019Low-Resource Parsing with Crosslingual Contextualized Representationscited by 5
- 2015One model, two languages: training bilingual parsers with harmonized treebankscited by 3
Built on by
Not cited yet.