Paradigm Completion for Derivational Morphology

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cotterell, Ryan, Vylomova, Ekaterina, Khayrallah, Huda, Kirov, Christo, Yarowsky, David
Format: Preprint
Published: 2017
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910828708495360
author Cotterell, Ryan
Vylomova, Ekaterina
Khayrallah, Huda
Kirov, Christo
Yarowsky, David
author_facet Cotterell, Ryan
Vylomova, Ekaterina
Khayrallah, Huda
Kirov, Christo
Yarowsky, David
contents The generation of complex derived word forms has been an overlooked problem in NLP; we fill this gap by applying neural sequence-to-sequence models to the task. We overview the theoretical motivation for a paradigmatic treatment of derivational morphology, and introduce the task of derivational paradigm completion as a parallel to inflectional paradigm completion. State-of-the-art neural models, adapted from the inflection task, are able to learn a range of derivation patterns, and outperform a non-neural baseline by 16.4%. However, due to semantic, historical, and lexical considerations involved in derivational morphology, future work will be needed to achieve performance parity with inflection-generating systems.
format Preprint
id arxiv_https___arxiv_org_abs_1708_09151
institution arXiv
publishDate 2017
record_format arxiv
spellingShingle Paradigm Completion for Derivational Morphology
Cotterell, Ryan
Vylomova, Ekaterina
Khayrallah, Huda
Kirov, Christo
Yarowsky, David
Computation and Language
The generation of complex derived word forms has been an overlooked problem in NLP; we fill this gap by applying neural sequence-to-sequence models to the task. We overview the theoretical motivation for a paradigmatic treatment of derivational morphology, and introduce the task of derivational paradigm completion as a parallel to inflectional paradigm completion. State-of-the-art neural models, adapted from the inflection task, are able to learn a range of derivation patterns, and outperform a non-neural baseline by 16.4%. However, due to semantic, historical, and lexical considerations involved in derivational morphology, future work will be needed to achieve performance parity with inflection-generating systems.
title Paradigm Completion for Derivational Morphology
topic Computation and Language
url https://arxiv.org/abs/1708.09151