@inproceedings{zalmout-habash-2020-joint,
title = "Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging",
author = "Zalmout, Nasser and
Habash, Nizar",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.736",
doi = "10.18653/v1/2020.acl-main.736",
pages = "8297--8307",
abstract = "The written forms of Semitic languages are both highly ambiguous and morphologically rich: a word can have multiple interpretations and is one of many inflected forms of the same concept or lemma. This is further exacerbated for dialectal content, which is more prone to noise and lacks a standard orthography. The morphological features can be lexicalized, like lemmas and diacritized forms, or non-lexicalized, like gender, number, and part-of-speech tags, among others. Joint modeling of the lexicalized and non-lexicalized features can identify more intricate morphological patterns, which provide better context modeling, and further disambiguate ambiguous lexical choices. However, the different modeling granularity can make joint modeling more difficult. Our approach models the different features jointly, whether lexicalized (on the character-level), or non-lexicalized (on the word-level). We use Arabic as a test case, and achieve state-of-the-art results for Modern Standard Arabic with 20{\%} relative error reduction, and Egyptian Arabic with 11{\%} relative error reduction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zalmout-habash-2020-joint">
<titleInfo>
<title>Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nasser</namePart>
<namePart type="family">Zalmout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The written forms of Semitic languages are both highly ambiguous and morphologically rich: a word can have multiple interpretations and is one of many inflected forms of the same concept or lemma. This is further exacerbated for dialectal content, which is more prone to noise and lacks a standard orthography. The morphological features can be lexicalized, like lemmas and diacritized forms, or non-lexicalized, like gender, number, and part-of-speech tags, among others. Joint modeling of the lexicalized and non-lexicalized features can identify more intricate morphological patterns, which provide better context modeling, and further disambiguate ambiguous lexical choices. However, the different modeling granularity can make joint modeling more difficult. Our approach models the different features jointly, whether lexicalized (on the character-level), or non-lexicalized (on the word-level). We use Arabic as a test case, and achieve state-of-the-art results for Modern Standard Arabic with 20% relative error reduction, and Egyptian Arabic with 11% relative error reduction.</abstract>
<identifier type="citekey">zalmout-habash-2020-joint</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.736</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.736</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>8297</start>
<end>8307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging
%A Zalmout, Nasser
%A Habash, Nizar
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F zalmout-habash-2020-joint
%X The written forms of Semitic languages are both highly ambiguous and morphologically rich: a word can have multiple interpretations and is one of many inflected forms of the same concept or lemma. This is further exacerbated for dialectal content, which is more prone to noise and lacks a standard orthography. The morphological features can be lexicalized, like lemmas and diacritized forms, or non-lexicalized, like gender, number, and part-of-speech tags, among others. Joint modeling of the lexicalized and non-lexicalized features can identify more intricate morphological patterns, which provide better context modeling, and further disambiguate ambiguous lexical choices. However, the different modeling granularity can make joint modeling more difficult. Our approach models the different features jointly, whether lexicalized (on the character-level), or non-lexicalized (on the word-level). We use Arabic as a test case, and achieve state-of-the-art results for Modern Standard Arabic with 20% relative error reduction, and Egyptian Arabic with 11% relative error reduction.
%R 10.18653/v1/2020.acl-main.736
%U https://aclanthology.org/2020.acl-main.736
%U https://doi.org/10.18653/v1/2020.acl-main.736
%P 8297-8307
Markdown (Informal)
[Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging](https://aclanthology.org/2020.acl-main.736) (Zalmout & Habash, ACL 2020)
ACL