<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-chen-2023-anchilm">
    <titleInfo>
        <title>AnchiLm: An Effective Classical-to-Modern Chinese Translation Model Leveraging bpe-drop and SikuRoBERTa</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiahui</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sizhou</namePart>
        <namePart type="family">Chen</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 ALT2023: Ancient Language Translation Workshop</title>
        </titleInfo>
        <originInfo>
            <publisher>Asia-Pacific Association for Machine Translation</publisher>
            <place>
                <placeTerm type="text">Macau SAR, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we present our submitted model for translating ancient to modern texts, which ranked sixth in the closed track of ancient Chinese in the 2nd International Review of Automatic Analysis of Ancient Chinese (EvaHan). Specifically, we employed two strategies to improve the translation from ancient to modern texts. First, we used bpe-drop to enhance the parallel corpus. Second, we use SikuRoBERTa to simultaneously initialize the translation model’s codec and reconstruct the bpe word list. In our experiments, we compare the baseline model, rdrop, pre-trained model, and parameter initialization methods. The experimental results show that the parameter initialization method in this paper significantly outperforms the baseline model in terms of performance, and its BLEU score reaches 21.75.</abstract>
    <identifier type="citekey">zhu-chen-2023-anchilm</identifier>
    <location>
        <url>https://aclanthology.org/2023.alt-1.8</url>
    </location>
    <part>
        <date>2023-09</date>
        <extent unit="page">
            <start>55</start>
            <end>60</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AnchiLm: An Effective Classical-to-Modern Chinese Translation Model Leveraging bpe-drop and SikuRoBERTa
%A Zhu, Jiahui
%A Chen, Sizhou
%S Proceedings of ALT2023: Ancient Language Translation Workshop
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F zhu-chen-2023-anchilm
%X In this paper, we present our submitted model for translating ancient to modern texts, which ranked sixth in the closed track of ancient Chinese in the 2nd International Review of Automatic Analysis of Ancient Chinese (EvaHan). Specifically, we employed two strategies to improve the translation from ancient to modern texts. First, we used bpe-drop to enhance the parallel corpus. Second, we use SikuRoBERTa to simultaneously initialize the translation model’s codec and reconstruct the bpe word list. In our experiments, we compare the baseline model, rdrop, pre-trained model, and parameter initialization methods. The experimental results show that the parameter initialization method in this paper significantly outperforms the baseline model in terms of performance, and its BLEU score reaches 21.75.
%U https://aclanthology.org/2023.alt-1.8
%P 55-60

Markdown (Informal)

[AnchiLm: An Effective Classical-to-Modern Chinese Translation Model Leveraging bpe-drop and SikuRoBERTa](https://aclanthology.org/2023.alt-1.8) (Zhu & Chen, alt 2023)

• AnchiLm: An Effective Classical-to-Modern Chinese Translation Model Leveraging bpe-drop and SikuRoBERTa (Zhu & Chen, alt 2023)

ACL

• Jiahui Zhu and Sizhou Chen. 2023. AnchiLm: An Effective Classical-to-Modern Chinese Translation Model Leveraging bpe-drop and SikuRoBERTa. In Proceedings of ALT2023: Ancient Language Translation Workshop, pages 55–60, Macau SAR, China. Asia-Pacific Association for Machine Translation.