@inproceedings{rao-etal-2021-cross-lingual,
title = "Cross-Lingual Leveled Reading Based on Language-Invariant Features",
author = "Rao, Simin and
Zheng, Hua and
Li, Sujian",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.227/",
doi = "10.18653/v1/2021.findings-emnlp.227",
pages = "2677--2682",
abstract = "Leveled reading (LR) aims to automatically classify texts by the cognitive levels of readers, which is fundamental in providing appropriate reading materials regarding different reading capabilities. However, most state-of-the-art LR methods rely on the availability of copious annotated resources, which prevents their adaptation to low-resource languages like Chinese. In our work, to tackle LR in Chinese, we explore how different language transfer methods perform on English-Chinese LR. Specifically, we focus on adversarial training and cross-lingual pre-training method to transfer the LR knowledge learned from annotated data in the resource-rich English language to Chinese. For evaluation, we first introduce the age-based standard to align datasets with different leveling standards. Then we conduct experiments in both zero-shot and few-shot settings. Comparing these two methods, quantitative and qualitative evaluations show that the cross-lingual pre-training method effectively captures the language-invariant features between English and Chinese. We conduct analysis to propose further improvement in cross-lingual LR."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rao-etal-2021-cross-lingual">
<titleInfo>
<title>Cross-Lingual Leveled Reading Based on Language-Invariant Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simin</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Leveled reading (LR) aims to automatically classify texts by the cognitive levels of readers, which is fundamental in providing appropriate reading materials regarding different reading capabilities. However, most state-of-the-art LR methods rely on the availability of copious annotated resources, which prevents their adaptation to low-resource languages like Chinese. In our work, to tackle LR in Chinese, we explore how different language transfer methods perform on English-Chinese LR. Specifically, we focus on adversarial training and cross-lingual pre-training method to transfer the LR knowledge learned from annotated data in the resource-rich English language to Chinese. For evaluation, we first introduce the age-based standard to align datasets with different leveling standards. Then we conduct experiments in both zero-shot and few-shot settings. Comparing these two methods, quantitative and qualitative evaluations show that the cross-lingual pre-training method effectively captures the language-invariant features between English and Chinese. We conduct analysis to propose further improvement in cross-lingual LR.</abstract>
<identifier type="citekey">rao-etal-2021-cross-lingual</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.227</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.227/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2677</start>
<end>2682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Leveled Reading Based on Language-Invariant Features
%A Rao, Simin
%A Zheng, Hua
%A Li, Sujian
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F rao-etal-2021-cross-lingual
%X Leveled reading (LR) aims to automatically classify texts by the cognitive levels of readers, which is fundamental in providing appropriate reading materials regarding different reading capabilities. However, most state-of-the-art LR methods rely on the availability of copious annotated resources, which prevents their adaptation to low-resource languages like Chinese. In our work, to tackle LR in Chinese, we explore how different language transfer methods perform on English-Chinese LR. Specifically, we focus on adversarial training and cross-lingual pre-training method to transfer the LR knowledge learned from annotated data in the resource-rich English language to Chinese. For evaluation, we first introduce the age-based standard to align datasets with different leveling standards. Then we conduct experiments in both zero-shot and few-shot settings. Comparing these two methods, quantitative and qualitative evaluations show that the cross-lingual pre-training method effectively captures the language-invariant features between English and Chinese. We conduct analysis to propose further improvement in cross-lingual LR.
%R 10.18653/v1/2021.findings-emnlp.227
%U https://aclanthology.org/2021.findings-emnlp.227/
%U https://doi.org/10.18653/v1/2021.findings-emnlp.227
%P 2677-2682
Markdown (Informal)
[Cross-Lingual Leveled Reading Based on Language-Invariant Features](https://aclanthology.org/2021.findings-emnlp.227/) (Rao et al., Findings 2021)
ACL