@inproceedings{nzeyimana-2020-morphological,
title = "Morphological disambiguation from stemming data",
author = "Nzeyimana, Antoine",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.409/",
doi = "10.18653/v1/2020.coling-main.409",
pages = "4649--4660",
abstract = "Morphological analysis and disambiguation is an important task and a crucial preprocessing step in natural language processing of morphologically rich languages. Kinyarwanda, a morphologically rich language, currently lacks tools for automated morphological analysis. While linguistically curated finite state tools can be easily developed for morphological analysis, the morphological richness of the language allows many ambiguous analyses to be produced, requiring effective disambiguation. In this paper, we propose learning to morphologically disambiguate Kinyarwanda verbal forms from a new stemming dataset collected through crowd-sourcing. Using feature engineering and a feed-forward neural network based classifier, we achieve about 89{\%} non-contextualized disambiguation accuracy. Our experiments reveal that inflectional properties of stems and morpheme association rules are the most discriminative features for disambiguation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nzeyimana-2020-morphological">
<titleInfo>
<title>Morphological disambiguation from stemming data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Nzeyimana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Morphological analysis and disambiguation is an important task and a crucial preprocessing step in natural language processing of morphologically rich languages. Kinyarwanda, a morphologically rich language, currently lacks tools for automated morphological analysis. While linguistically curated finite state tools can be easily developed for morphological analysis, the morphological richness of the language allows many ambiguous analyses to be produced, requiring effective disambiguation. In this paper, we propose learning to morphologically disambiguate Kinyarwanda verbal forms from a new stemming dataset collected through crowd-sourcing. Using feature engineering and a feed-forward neural network based classifier, we achieve about 89% non-contextualized disambiguation accuracy. Our experiments reveal that inflectional properties of stems and morpheme association rules are the most discriminative features for disambiguation.</abstract>
<identifier type="citekey">nzeyimana-2020-morphological</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.409</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.409/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4649</start>
<end>4660</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphological disambiguation from stemming data
%A Nzeyimana, Antoine
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F nzeyimana-2020-morphological
%X Morphological analysis and disambiguation is an important task and a crucial preprocessing step in natural language processing of morphologically rich languages. Kinyarwanda, a morphologically rich language, currently lacks tools for automated morphological analysis. While linguistically curated finite state tools can be easily developed for morphological analysis, the morphological richness of the language allows many ambiguous analyses to be produced, requiring effective disambiguation. In this paper, we propose learning to morphologically disambiguate Kinyarwanda verbal forms from a new stemming dataset collected through crowd-sourcing. Using feature engineering and a feed-forward neural network based classifier, we achieve about 89% non-contextualized disambiguation accuracy. Our experiments reveal that inflectional properties of stems and morpheme association rules are the most discriminative features for disambiguation.
%R 10.18653/v1/2020.coling-main.409
%U https://aclanthology.org/2020.coling-main.409/
%U https://doi.org/10.18653/v1/2020.coling-main.409
%P 4649-4660
Markdown (Informal)
[Morphological disambiguation from stemming data](https://aclanthology.org/2020.coling-main.409/) (Nzeyimana, COLING 2020)
ACL
- Antoine Nzeyimana. 2020. Morphological disambiguation from stemming data. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4649–4660, Barcelona, Spain (Online). International Committee on Computational Linguistics.