@inproceedings{wang-liu-and-james-hearne-2022-shot,
title = "Few-shot Learning for {S}umerian Named Entity Recognition",
author = "Wang, Guanghai and
Liu, Yudong and
Hearne, James",
editor = "Cherry, Colin and
Fan, Angela and
Foster, George and
Haffari, Gholamreza (Reza) and
Khadivi, Shahram and
Peng, Nanyun (Violet) and
Ren, Xiang and
Shareghi, Ehsan and
Swayamdipta, Swabha",
booktitle = "Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing",
month = jul,
year = "2022",
address = "Hybrid",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.deeplo-1.15",
doi = "10.18653/v1/2022.deeplo-1.15",
pages = "136--145",
abstract = "This paper presents our study in exploring the task of named entity recognition (NER) in a low resource setting, focusing on few-shot learning on the Sumerian NER task. The Sumerian language is deemed as an extremely low-resource language due to that (1) it is a long dead language, (2) highly skilled language experts are extremely scarce. NER on Sumerian text is important in that it helps identify the actors and entities active in a given period of time from the collections of tens of thousands of texts in building socio-economic networks of the archives of interest. As a text classification task, NER tends to become challenging when the amount of annotated data is limited or the model is required to handle new classes. The Sumerian NER is no exception. In this work, we propose to use two few-shot learning systems, ProtoBERT and NNShot, to the Sumerian NER task. Our experiments show that the ProtoBERT NER generally outperforms both the NNShot NER and the fully supervised BERT NER in low resource settings on the predictions of rare classes. In particular, F1-score of ProtoBERT on unseen entity types on our test set has achieved 89.6{\%} that is significantly better than the F1-score of 84.3{\%} of the BERT NER.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-liu-and-james-hearne-2022-shot">
<titleInfo>
<title>Few-shot Learning for Sumerian Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guanghai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Hearne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="given">(Reza)</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="given">(Violet)</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our study in exploring the task of named entity recognition (NER) in a low resource setting, focusing on few-shot learning on the Sumerian NER task. The Sumerian language is deemed as an extremely low-resource language due to that (1) it is a long dead language, (2) highly skilled language experts are extremely scarce. NER on Sumerian text is important in that it helps identify the actors and entities active in a given period of time from the collections of tens of thousands of texts in building socio-economic networks of the archives of interest. As a text classification task, NER tends to become challenging when the amount of annotated data is limited or the model is required to handle new classes. The Sumerian NER is no exception. In this work, we propose to use two few-shot learning systems, ProtoBERT and NNShot, to the Sumerian NER task. Our experiments show that the ProtoBERT NER generally outperforms both the NNShot NER and the fully supervised BERT NER in low resource settings on the predictions of rare classes. In particular, F1-score of ProtoBERT on unseen entity types on our test set has achieved 89.6% that is significantly better than the F1-score of 84.3% of the BERT NER.</abstract>
<identifier type="citekey">wang-liu-and-james-hearne-2022-shot</identifier>
<identifier type="doi">10.18653/v1/2022.deeplo-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.deeplo-1.15</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>136</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-shot Learning for Sumerian Named Entity Recognition
%A Wang, Guanghai
%A Liu, Yudong
%A Hearne, James
%Y Cherry, Colin
%Y Fan, Angela
%Y Foster, George
%Y Haffari, Gholamreza (Reza)
%Y Khadivi, Shahram
%Y Peng, Nanyun (Violet)
%Y Ren, Xiang
%Y Shareghi, Ehsan
%Y Swayamdipta, Swabha
%S Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid
%F wang-liu-and-james-hearne-2022-shot
%X This paper presents our study in exploring the task of named entity recognition (NER) in a low resource setting, focusing on few-shot learning on the Sumerian NER task. The Sumerian language is deemed as an extremely low-resource language due to that (1) it is a long dead language, (2) highly skilled language experts are extremely scarce. NER on Sumerian text is important in that it helps identify the actors and entities active in a given period of time from the collections of tens of thousands of texts in building socio-economic networks of the archives of interest. As a text classification task, NER tends to become challenging when the amount of annotated data is limited or the model is required to handle new classes. The Sumerian NER is no exception. In this work, we propose to use two few-shot learning systems, ProtoBERT and NNShot, to the Sumerian NER task. Our experiments show that the ProtoBERT NER generally outperforms both the NNShot NER and the fully supervised BERT NER in low resource settings on the predictions of rare classes. In particular, F1-score of ProtoBERT on unseen entity types on our test set has achieved 89.6% that is significantly better than the F1-score of 84.3% of the BERT NER.
%R 10.18653/v1/2022.deeplo-1.15
%U https://aclanthology.org/2022.deeplo-1.15
%U https://doi.org/10.18653/v1/2022.deeplo-1.15
%P 136-145
Markdown (Informal)
[Few-shot Learning for Sumerian Named Entity Recognition](https://aclanthology.org/2022.deeplo-1.15) (Wang et al., DeepLo 2022)
ACL