@inproceedings{sagare-etal-2023-xf2t,
title = "{XF}2{T}: Cross-lingual Fact-to-Text Generation for Low-Resource Languages",
author = "Sagare, Shivprasad and
Abhishek, Tushar and
Singh, Bhavyajeet and
Sharma, Anubhav and
Gupta, Manish and
Varma, Vasudeva",
editor = "Keet, C. Maria and
Lee, Hung-Yi and
Zarrie{\ss}, Sina",
booktitle = "Proceedings of the 16th International Natural Language Generation Conference",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.inlg-main.2",
doi = "10.18653/v1/2023.inlg-main.2",
pages = "15--27",
abstract = "Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. This has resulted into substantial work on fact-to-text generation systems recently. Unfortunately, previous work on fact-to-text (F2T) generation has focused primarily on English mainly due to the high availability of relevant datasets. Only recently, the problem of cross-lingual fact-to-text (XF2T) was proposed for generation across multiple languages alongwith a dataset, XAlign for eight languages. However, there has been no rigorous work on the actual XF2T generation problem. We extend XAlign dataset with annotated data for four more languages: Punjabi, Malayalam, Assamese and Oriya. We conduct an extensive study using popular Transformer-based text generation models on our extended multi-lingual dataset, which we call XAlignV2. Further, we investigate the performance of different text generation strategies: multiple variations of pretraining, fact-aware embeddings and structure-aware input encoding. Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results (30.90 BLEU, 55.12 METEOR and 59.17 chrF++) across the twelve languages. We make our code, dataset and model publicly available, and hope that this will help advance further research in this critical area.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sagare-etal-2023-xf2t">
<titleInfo>
<title>XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shivprasad</namePart>
<namePart type="family">Sagare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tushar</namePart>
<namePart type="family">Abhishek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhavyajeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anubhav</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasudeva</namePart>
<namePart type="family">Varma</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 16th International Natural Language Generation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Keet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. This has resulted into substantial work on fact-to-text generation systems recently. Unfortunately, previous work on fact-to-text (F2T) generation has focused primarily on English mainly due to the high availability of relevant datasets. Only recently, the problem of cross-lingual fact-to-text (XF2T) was proposed for generation across multiple languages alongwith a dataset, XAlign for eight languages. However, there has been no rigorous work on the actual XF2T generation problem. We extend XAlign dataset with annotated data for four more languages: Punjabi, Malayalam, Assamese and Oriya. We conduct an extensive study using popular Transformer-based text generation models on our extended multi-lingual dataset, which we call XAlignV2. Further, we investigate the performance of different text generation strategies: multiple variations of pretraining, fact-aware embeddings and structure-aware input encoding. Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results (30.90 BLEU, 55.12 METEOR and 59.17 chrF++) across the twelve languages. We make our code, dataset and model publicly available, and hope that this will help advance further research in this critical area.</abstract>
<identifier type="citekey">sagare-etal-2023-xf2t</identifier>
<identifier type="doi">10.18653/v1/2023.inlg-main.2</identifier>
<location>
<url>https://aclanthology.org/2023.inlg-main.2</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>15</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages
%A Sagare, Shivprasad
%A Abhishek, Tushar
%A Singh, Bhavyajeet
%A Sharma, Anubhav
%A Gupta, Manish
%A Varma, Vasudeva
%Y Keet, C. Maria
%Y Lee, Hung-Yi
%Y Zarrieß, Sina
%S Proceedings of the 16th International Natural Language Generation Conference
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F sagare-etal-2023-xf2t
%X Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. This has resulted into substantial work on fact-to-text generation systems recently. Unfortunately, previous work on fact-to-text (F2T) generation has focused primarily on English mainly due to the high availability of relevant datasets. Only recently, the problem of cross-lingual fact-to-text (XF2T) was proposed for generation across multiple languages alongwith a dataset, XAlign for eight languages. However, there has been no rigorous work on the actual XF2T generation problem. We extend XAlign dataset with annotated data for four more languages: Punjabi, Malayalam, Assamese and Oriya. We conduct an extensive study using popular Transformer-based text generation models on our extended multi-lingual dataset, which we call XAlignV2. Further, we investigate the performance of different text generation strategies: multiple variations of pretraining, fact-aware embeddings and structure-aware input encoding. Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results (30.90 BLEU, 55.12 METEOR and 59.17 chrF++) across the twelve languages. We make our code, dataset and model publicly available, and hope that this will help advance further research in this critical area.
%R 10.18653/v1/2023.inlg-main.2
%U https://aclanthology.org/2023.inlg-main.2
%U https://doi.org/10.18653/v1/2023.inlg-main.2
%P 15-27
Markdown (Informal)
[XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages](https://aclanthology.org/2023.inlg-main.2) (Sagare et al., INLG-SIGDIAL 2023)
ACL