Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology

R Zmigrod, SJ Mielke, H Wallach, R Cotterell - ar** contextsensitive lemmatizers is to improve performance
on unseen and ambiguous words. Yet previous systems have not carefully evaluated …

A survey on syntactic processing techniques

X Zhang, R Mao, E Cambria - Artificial Intelligence Review, 2023 - Springer
Computational syntactic processing is a fundamental technique in natural language
processing. It normally serves as a pre-processing method to transform natural language …

[PDF][PDF] MED: The LMU system for the SIGMORPHON 2016 shared task on morphological reinflection

K Kann, H Schütze - … of the 14th SIGMORPHON Workshop on …, 2016 - aclanthology.org
This paper presents MED, the main system of the LMU team for the SIGMORPHON 2016
Shared Task on Morphological Reinflection as well as an extended analysis of how different …

Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks

J Kanerva, F Ginter, T Salakoski - Natural Language Engineering, 2021 - cambridge.org
In this paper, we present a novel lemmatization method based on a sequence-to-sequence
neural network architecture and morphosyntactic context representation. In the proposed …

Cross-lingual, character-level neural morphological tagging

R Cotterell, G Heigold - arxiv preprint arxiv:1708.09157, 2017 - arxiv.org
Even for common NLP tasks, sufficient supervision is not available in many languages--
morphological tagging is no exception. In the work presented here, we explore a transfer …