@inproceedings{long-an-2023-development,
title = "On the Development of Interlinearized Ancient Literature of Ethnic Minorities: A Case Study of the Interlinearization of Ancient Written {T}ibetan Literature",
author = "Long, Congjun and
An, Bo",
editor = "Anderson, Adam and
Gordin, Shai and
Li, Bin and
Liu, Yudong and
Passarotti, Marco C.",
booktitle = "Proceedings of the Ancient Language Processing Workshop",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.alp-1.25",
pages = "222--231",
abstract = "Ancient ethnic documents are essential to China{'}s ancient literature and an indispensable civilizational achievement of Chinese culture. However, few research teams are involved due to language and script literacy limitations. To address these issues, this paper proposes an interlinearized annotation strategy for ancient ethnic literature. This strategy aims to alleviate text literacy difficulties, encourage interdisciplinary researchers to participate in studying ancient ethnic literature, and improve the efficiency of ancient ethnic literature development. Concretely, the interlinearized annotation consists of original, word segmentation, Latin, annotated, and translation lines. In this paper, we take ancient Tibetan literature as an example to explore the interlinearized annotation strategy. However, manually building large-scale corpus is challenging. To build a large-scale interlinearized dataset, we propose a multi-task learning-based interlinearized annotation method, which can generate interlinearized annotation lines based on the original line. Experimental results show that after training on about 10,000 sentences (lines) of data, our model achieves 70.9{\%} and 63.2{\%} F1 values on the segmentation lines and annotated lines, respectively, and 18.7{\%} BLEU on the translation lines. It dramatically enhances the efficiency of data annotation, effectively speeds up interlinearized annotation, and reduces the workload of manual annotation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="long-an-2023-development">
<titleInfo>
<title>On the Development of Interlinearized Ancient Literature of Ethnic Minorities: A Case Study of the Interlinearization of Ancient Written Tibetan Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Congjun</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ancient Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ancient ethnic documents are essential to China’s ancient literature and an indispensable civilizational achievement of Chinese culture. However, few research teams are involved due to language and script literacy limitations. To address these issues, this paper proposes an interlinearized annotation strategy for ancient ethnic literature. This strategy aims to alleviate text literacy difficulties, encourage interdisciplinary researchers to participate in studying ancient ethnic literature, and improve the efficiency of ancient ethnic literature development. Concretely, the interlinearized annotation consists of original, word segmentation, Latin, annotated, and translation lines. In this paper, we take ancient Tibetan literature as an example to explore the interlinearized annotation strategy. However, manually building large-scale corpus is challenging. To build a large-scale interlinearized dataset, we propose a multi-task learning-based interlinearized annotation method, which can generate interlinearized annotation lines based on the original line. Experimental results show that after training on about 10,000 sentences (lines) of data, our model achieves 70.9% and 63.2% F1 values on the segmentation lines and annotated lines, respectively, and 18.7% BLEU on the translation lines. It dramatically enhances the efficiency of data annotation, effectively speeds up interlinearized annotation, and reduces the workload of manual annotation.</abstract>
<identifier type="citekey">long-an-2023-development</identifier>
<location>
<url>https://aclanthology.org/2023.alp-1.25</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>222</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Development of Interlinearized Ancient Literature of Ethnic Minorities: A Case Study of the Interlinearization of Ancient Written Tibetan Literature
%A Long, Congjun
%A An, Bo
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%S Proceedings of the Ancient Language Processing Workshop
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F long-an-2023-development
%X Ancient ethnic documents are essential to China’s ancient literature and an indispensable civilizational achievement of Chinese culture. However, few research teams are involved due to language and script literacy limitations. To address these issues, this paper proposes an interlinearized annotation strategy for ancient ethnic literature. This strategy aims to alleviate text literacy difficulties, encourage interdisciplinary researchers to participate in studying ancient ethnic literature, and improve the efficiency of ancient ethnic literature development. Concretely, the interlinearized annotation consists of original, word segmentation, Latin, annotated, and translation lines. In this paper, we take ancient Tibetan literature as an example to explore the interlinearized annotation strategy. However, manually building large-scale corpus is challenging. To build a large-scale interlinearized dataset, we propose a multi-task learning-based interlinearized annotation method, which can generate interlinearized annotation lines based on the original line. Experimental results show that after training on about 10,000 sentences (lines) of data, our model achieves 70.9% and 63.2% F1 values on the segmentation lines and annotated lines, respectively, and 18.7% BLEU on the translation lines. It dramatically enhances the efficiency of data annotation, effectively speeds up interlinearized annotation, and reduces the workload of manual annotation.
%U https://aclanthology.org/2023.alp-1.25
%P 222-231
Markdown (Informal)
[On the Development of Interlinearized Ancient Literature of Ethnic Minorities: A Case Study of the Interlinearization of Ancient Written Tibetan Literature](https://aclanthology.org/2023.alp-1.25) (Long & An, ALP-WS 2023)
ACL