<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2022-manifolds">
    <titleInfo>
        <title>Manifold’s English-Chinese System at WMT22 General MT Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chang</namePart>
        <namePart type="family">Jin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tingxun</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhengshan</namePart>
        <namePart type="family">Xue</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaodong</namePart>
        <namePart type="family">Lin</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 Seventh Conference on Machine Translation (WMT)</title>
        </titleInfo>
        <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>Manifold’s English-Chinese System at WMT22 is an ensemble of 4 models trained by different configurations with scheduled sampling-based fine-tuning. The four configurations are DeepBig (XenC), DeepLarger (XenC), DeepBig-TalkingHeads (XenC) and DeepBig (LaBSE). Concretely, DeepBig extends Transformer-Big to 24 encoder layers. DeepLarger has 20 encoder layers and its feed-forward network (FFN) dimension is 8192. TalkingHeads applies the talking-heads trick. For XenC configs, we selected monolingual and parallel data that is similar to the past newstest datasets using XenC, and for LaBSE, we cleaned the officially provided parallel data using LaBSE pretrained model. According to the officially released autonomic metrics leaderboard, our final constrained system ranked 1st among all others when evaluated by bleu-all, chrf-all and COMET-B, 2nd by COMET-A.</abstract>
    <identifier type="citekey">jin-etal-2022-manifolds</identifier>
    <location>
        <url>https://aclanthology.org/2022.wmt-1.20</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>275</start>
            <end>279</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Manifold’s English-Chinese System at WMT22 General MT Task
%A Jin, Chang
%A Shi, Tingxun
%A Xue, Zhengshan
%A Lin, Xiaodong
%S Proceedings of the Seventh Conference on Machine Translation (WMT)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F jin-etal-2022-manifolds
%X Manifold’s English-Chinese System at WMT22 is an ensemble of 4 models trained by different configurations with scheduled sampling-based fine-tuning. The four configurations are DeepBig (XenC), DeepLarger (XenC), DeepBig-TalkingHeads (XenC) and DeepBig (LaBSE). Concretely, DeepBig extends Transformer-Big to 24 encoder layers. DeepLarger has 20 encoder layers and its feed-forward network (FFN) dimension is 8192. TalkingHeads applies the talking-heads trick. For XenC configs, we selected monolingual and parallel data that is similar to the past newstest datasets using XenC, and for LaBSE, we cleaned the officially provided parallel data using LaBSE pretrained model. According to the officially released autonomic metrics leaderboard, our final constrained system ranked 1st among all others when evaluated by bleu-all, chrf-all and COMET-B, 2nd by COMET-A.
%U https://aclanthology.org/2022.wmt-1.20
%P 275-279

Markdown (Informal)

[Manifold’s English-Chinese System at WMT22 General MT Task](https://aclanthology.org/2022.wmt-1.20) (Jin et al., WMT 2022)

• Manifold’s English-Chinese System at WMT22 General MT Task (Jin et al., WMT 2022)

ACL

• Chang Jin, Tingxun Shi, Zhengshan Xue, and Xiaodong Lin. 2022. Manifold’s English-Chinese System at WMT22 General MT Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 275–279, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.