@inproceedings{seyoum-etal-2020-comparing,
title = "Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: {A}mharic Dependency Parser",
author = "Seyoum, Binyam Ephrem and
Miyao, Yusuke and
Mekonnen, Baye Yimam",
editor = "Mabuya, Rooweither and
Ramukhadi, Phathutshedzo and
Setaka, Mmasibidi and
Wagner, Valencia and
van Zaanen, Menno",
booktitle = "Proceedings of the first workshop on Resources for African Indigenous Languages",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.rail-1.5/",
pages = "25--30",
language = "eng",
ISBN = "979-10-95546-60-3",
abstract = "In this paper, we compare four state-of-the-art neural network dependency parsers for the Semitic language Amharic. As Amharic is a morphologically-rich and less-resourced language, the out-of-vocabulary (OOV) problem will be higher when we develop data-driven models. This fact limits researchers to develop neural network parsers because the neural network requires large quantities of data to train a model. We empirically evaluate neural network parsers when a small Amharic treebank is used for training. Based on our experiment, we obtain an 83.79 LAS score using the UDPipe system. Better accuracy is achieved when the neural parsing system uses external resources like word embedding. Using such resources, the LAS score for UDPipe improves to 85.26. Our experiment shows that the neural networks can learn dependency relations better from limited data while segmentation and POS tagging require much data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seyoum-etal-2020-comparing">
<titleInfo>
<title>Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: Amharic Dependency Parser</title>
</titleInfo>
<name type="personal">
<namePart type="given">Binyam</namePart>
<namePart type="given">Ephrem</namePart>
<namePart type="family">Seyoum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baye</namePart>
<namePart type="given">Yimam</namePart>
<namePart type="family">Mekonnen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the first workshop on Resources for African Indigenous Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phathutshedzo</namePart>
<namePart type="family">Ramukhadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valencia</namePart>
<namePart type="family">Wagner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-60-3</identifier>
</relatedItem>
<abstract>In this paper, we compare four state-of-the-art neural network dependency parsers for the Semitic language Amharic. As Amharic is a morphologically-rich and less-resourced language, the out-of-vocabulary (OOV) problem will be higher when we develop data-driven models. This fact limits researchers to develop neural network parsers because the neural network requires large quantities of data to train a model. We empirically evaluate neural network parsers when a small Amharic treebank is used for training. Based on our experiment, we obtain an 83.79 LAS score using the UDPipe system. Better accuracy is achieved when the neural parsing system uses external resources like word embedding. Using such resources, the LAS score for UDPipe improves to 85.26. Our experiment shows that the neural networks can learn dependency relations better from limited data while segmentation and POS tagging require much data.</abstract>
<identifier type="citekey">seyoum-etal-2020-comparing</identifier>
<location>
<url>https://aclanthology.org/2020.rail-1.5/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>25</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: Amharic Dependency Parser
%A Seyoum, Binyam Ephrem
%A Miyao, Yusuke
%A Mekonnen, Baye Yimam
%Y Mabuya, Rooweither
%Y Ramukhadi, Phathutshedzo
%Y Setaka, Mmasibidi
%Y Wagner, Valencia
%Y van Zaanen, Menno
%S Proceedings of the first workshop on Resources for African Indigenous Languages
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-60-3
%G eng
%F seyoum-etal-2020-comparing
%X In this paper, we compare four state-of-the-art neural network dependency parsers for the Semitic language Amharic. As Amharic is a morphologically-rich and less-resourced language, the out-of-vocabulary (OOV) problem will be higher when we develop data-driven models. This fact limits researchers to develop neural network parsers because the neural network requires large quantities of data to train a model. We empirically evaluate neural network parsers when a small Amharic treebank is used for training. Based on our experiment, we obtain an 83.79 LAS score using the UDPipe system. Better accuracy is achieved when the neural parsing system uses external resources like word embedding. Using such resources, the LAS score for UDPipe improves to 85.26. Our experiment shows that the neural networks can learn dependency relations better from limited data while segmentation and POS tagging require much data.
%U https://aclanthology.org/2020.rail-1.5/
%P 25-30
Markdown (Informal)
[Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: Amharic Dependency Parser](https://aclanthology.org/2020.rail-1.5/) (Seyoum et al., RAIL 2020)
ACL