Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Morphological Complexity in Synthetic Data and Zero-Shot GED Performance on Agglutinative Languages

Domain:

natural language processing

Record type:

paper
Creator:
Ass
Publisher:
Zenodo
Host:avatar
Grammatical Error Detection (GED) methods rely heavily on human annotated error corpora. However, these annotations are unavailable in many low-resource languages. In this paper, we investigate GED in this context. Leveraging the zero-shot cross-lingual transfer capabilities of multilingual pre-trained language models, we train a model using data from a diverse set of languages to generate synthetic errors in other languages. These synthetic error corpora are then used to train a GED model. Specifically we propose a two-stage fine-tuning pipeline where the GED model is first fine-tuned on mult Research goal: How does the morphological complexity of source languages in synthetic data generation impact the F1 score of zero-shot Grammatical Error Detection on agglutinative target languages? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 9.2/10.

Visit

doi.orgzenodo.org

Tasks

grammar error correctiontransfer learning

Tags

morphologicalcomplexitysourcelanguagessyntheticdatagenerationimpact

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

Comparative Performance of Zero-Shot Synthetic Error Data and Human Annotations on Low-Resource Languages in FLORES-200Robustness Analysis of Zero-Shot Cross-Lingual GED Models on Low-Resource LanguagesCode-Switched Token Ratios in Synthetic Data and Multilingual Encoder Performance on Zero-Shot BEIR RetrievalScaling Performance of Zero-Shot Cross-Lingual Retrievers Trained on Synthetic Code-Switched Data on XTREMEGrammatical Error Detection Performance in Low-Resource Languages: Zero-Shot Synthetic vs. Human-Annotated BaselinesPerformance comparison of synthetic error data via zero-shot cross-lingual transfer and human-annotated data on CoNLL-14 benchmark

Comparative Performance of Zero-Shot Synthetic Error Data and Human Annotations on Low-Resource Languages in FLORES-200

Grammatical Error Detection (GED) methods rely heavily on human annotated error corpora. However, th

Robustness Analysis of Zero-Shot Cross-Lingual GED Models on Low-Resource Languages

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Code-Switched Token Ratios in Synthetic Data and Multilingual Encoder Performance on Zero-Shot BEIR Retrieval

Transferring information retrieval (IR) models from a high-resource language (typically English) to

Scaling Performance of Zero-Shot Cross-Lingual Retrievers Trained on Synthetic Code-Switched Data on XTREME

Transferring information retrieval (IR) models from a high-resource language (typically English) to

Grammatical Error Detection Performance in Low-Resource Languages: Zero-Shot Synthetic vs. Human-Annotated Baselines

Grammatical Error Detection (GED) methods rely heavily on human annotated error corpora. However, th

Performance comparison of synthetic error data via zero-shot cross-lingual transfer and human-annotated data on CoNLL-14 benchmark

Grammatical Error Detection (GED) methods rely heavily on human annotated error corpora. However, th