Papers by Akhilesh Kakolu Ramarao

1 papers
Frequency matters: Modeling irregular morphological patterns in Spanish with Transformers (2025.findings-acl)

Copied to clipboard

Challenge: A common generation task in morphology is morphological inflection, where a target form has to be generated from its corresponding lemma and feature tag.
Approach: They propose to solve the Paradigm Cell Filling Problem (PCFP) by using encoder-decoder transformers to generate inflected verbs in Spanish.
Outcome: The proposed model performs better on L-shaped verbs than regular verbs, but no consistent recency effects are observed.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations