Saved in:
Bibliographic Details
Main Authors: Devadiga, Prathamesh, Shetty, Omkaar Jayadev, Nachnani, Hiya, R, Prema
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.15836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912548225286144
author Devadiga, Prathamesh
Shetty, Omkaar Jayadev
Nachnani, Hiya
R, Prema
author_facet Devadiga, Prathamesh
Shetty, Omkaar Jayadev
Nachnani, Hiya
R, Prema
contents Morphologically complex languages, particularly multiscript Indian languages, present significant challenges for Natural Language Processing (NLP). This work introduces MorphNAS, a novel differentiable neural architecture search framework designed to address these challenges. MorphNAS enhances Differentiable Architecture Search (DARTS) by incorporating linguistic meta-features such as script type and morphological complexity to optimize neural architectures for Named Entity Recognition (NER). It automatically identifies optimal micro-architectural elements tailored to language-specific morphology. By automating this search, MorphNAS aims to maximize the proficiency of multilingual NLP models, leading to improved comprehension and processing of these complex languages.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15836
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MorphNAS: Differentiable Architecture Search for Morphologically-Aware Multilingual NER
Devadiga, Prathamesh
Shetty, Omkaar Jayadev
Nachnani, Hiya
R, Prema
Computation and Language
Artificial Intelligence
Machine Learning
Morphologically complex languages, particularly multiscript Indian languages, present significant challenges for Natural Language Processing (NLP). This work introduces MorphNAS, a novel differentiable neural architecture search framework designed to address these challenges. MorphNAS enhances Differentiable Architecture Search (DARTS) by incorporating linguistic meta-features such as script type and morphological complexity to optimize neural architectures for Named Entity Recognition (NER). It automatically identifies optimal micro-architectural elements tailored to language-specific morphology. By automating this search, MorphNAS aims to maximize the proficiency of multilingual NLP models, leading to improved comprehension and processing of these complex languages.
title MorphNAS: Differentiable Architecture Search for Morphologically-Aware Multilingual NER
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.15836