@inproceedings{eskander-etal-2022-towards,
title = "Towards Improved Distantly Supervised Multilingual Named-Entity Recognition for Tweets",
author = "Eskander, Ramy and
Mishra, Shubhanshu and
Mehta, Sneha and
Samaniego, Sofia and
Haghighi, Aria",
editor = {Ataman, Duygu and
Gonen, Hila and
Ruder, Sebastian and
Firat, Orhan and
G{\"u}l Sahin, G{\"o}zde and
Mirzakhalov, Jamshidbek},
booktitle = "Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.mrl-1.12",
doi = "10.18653/v1/2022.mrl-1.12",
pages = "115--124",
abstract = "Recent low-resource named-entity recognition (NER) work has shown impressive gains by leveraging a single multilingual model trained using distantly supervised data derived from cross-lingual knowledge bases. In this work, we investigate such approaches by leveraging Wikidata to build large-scale NER datasets of Tweets and propose two orthogonal improvements for low-resource NER in the Twitter social media domain: (1) leveraging domain-specific pre-training on Tweets; and (2) building a model for each language family rather than an all-in-one single multilingual model. For (1), we show that mBERT with Tweet pre-training outperforms the state-of-the-art multilingual transformer-based language model, LaBSE, by a relative increase of 34.6{\%} in F1 when evaluated on Twitter data in a language-agnostic multilingual setting. For (2), we show that learning NER models for language families outperforms a single multilingual model by relative increases of 14.1{\%}, 15.8{\%} and 45.3{\%} in F1 when utilizing mBERT, mBERT with Tweet pre-training and LaBSE, respectively. We conduct analyses and present examples for these observed improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eskander-etal-2022-towards">
<titleInfo>
<title>Towards Improved Distantly Supervised Multilingual Named-Entity Recognition for Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubhanshu</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sneha</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofia</namePart>
<namePart type="family">Samaniego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aria</namePart>
<namePart type="family">Haghighi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orhan</namePart>
<namePart type="family">Firat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gözde</namePart>
<namePart type="family">Gül Sahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamshidbek</namePart>
<namePart type="family">Mirzakhalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent low-resource named-entity recognition (NER) work has shown impressive gains by leveraging a single multilingual model trained using distantly supervised data derived from cross-lingual knowledge bases. In this work, we investigate such approaches by leveraging Wikidata to build large-scale NER datasets of Tweets and propose two orthogonal improvements for low-resource NER in the Twitter social media domain: (1) leveraging domain-specific pre-training on Tweets; and (2) building a model for each language family rather than an all-in-one single multilingual model. For (1), we show that mBERT with Tweet pre-training outperforms the state-of-the-art multilingual transformer-based language model, LaBSE, by a relative increase of 34.6% in F1 when evaluated on Twitter data in a language-agnostic multilingual setting. For (2), we show that learning NER models for language families outperforms a single multilingual model by relative increases of 14.1%, 15.8% and 45.3% in F1 when utilizing mBERT, mBERT with Tweet pre-training and LaBSE, respectively. We conduct analyses and present examples for these observed improvements.</abstract>
<identifier type="citekey">eskander-etal-2022-towards</identifier>
<identifier type="doi">10.18653/v1/2022.mrl-1.12</identifier>
<location>
<url>https://aclanthology.org/2022.mrl-1.12</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>115</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Improved Distantly Supervised Multilingual Named-Entity Recognition for Tweets
%A Eskander, Ramy
%A Mishra, Shubhanshu
%A Mehta, Sneha
%A Samaniego, Sofia
%A Haghighi, Aria
%Y Ataman, Duygu
%Y Gonen, Hila
%Y Ruder, Sebastian
%Y Firat, Orhan
%Y Gül Sahin, Gözde
%Y Mirzakhalov, Jamshidbek
%S Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F eskander-etal-2022-towards
%X Recent low-resource named-entity recognition (NER) work has shown impressive gains by leveraging a single multilingual model trained using distantly supervised data derived from cross-lingual knowledge bases. In this work, we investigate such approaches by leveraging Wikidata to build large-scale NER datasets of Tweets and propose two orthogonal improvements for low-resource NER in the Twitter social media domain: (1) leveraging domain-specific pre-training on Tweets; and (2) building a model for each language family rather than an all-in-one single multilingual model. For (1), we show that mBERT with Tweet pre-training outperforms the state-of-the-art multilingual transformer-based language model, LaBSE, by a relative increase of 34.6% in F1 when evaluated on Twitter data in a language-agnostic multilingual setting. For (2), we show that learning NER models for language families outperforms a single multilingual model by relative increases of 14.1%, 15.8% and 45.3% in F1 when utilizing mBERT, mBERT with Tweet pre-training and LaBSE, respectively. We conduct analyses and present examples for these observed improvements.
%R 10.18653/v1/2022.mrl-1.12
%U https://aclanthology.org/2022.mrl-1.12
%U https://doi.org/10.18653/v1/2022.mrl-1.12
%P 115-124
Markdown (Informal)
[Towards Improved Distantly Supervised Multilingual Named-Entity Recognition for Tweets](https://aclanthology.org/2022.mrl-1.12) (Eskander et al., MRL 2022)
ACL