@inproceedings{lorincz-etal-2022-transfer,
title = "Transfer learning for multilingual vacancy text generation",
author = "Lorincz, Anna and
Graus, David and
Lavi, Dor and
Pereira, Joao Lebre Magalhaes",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.18",
doi = "10.18653/v1/2022.gem-1.18",
pages = "207--222",
abstract = "Writing job vacancies is a repetitive and expensive task for humans. This research focuses on automatically generating the benefit sections of vacancies at redacted from job attributes using mT5, the multilingual version of the state-of-the-art T5 transformer trained on general domains to generate texts in multiple languages. While transformers are accurate at generating coherent text, they are sometimes incorrect at including the structured data (the input) in the generated text. Including the input correctly is crucial for vacancy text generation; otherwise, the candidates may get misled. To evaluate how the model includes the input we developed our own domain-specific metrics (input generation accuracy). This was necessary, because Relation Generation, the pre-existing evaluation metric for data-to-text generation uses only string matching, which was not suitable for our dataset (due to the binary field). With the help of the new evaluation method we were able to measure how well the input is included in the generated text separately for different types of inputs (binary, categorical, numeric), offering another contribution to the field. Additionally, we also evaluated how accurate the mT5 model generates the text in the requested language. The results show that mT5 is very accurate at generating the text in the correct language, at including seen categorical inputs and binary values correctly in the generated text. However, mT5 performed worse when generating text from unseen city names or working with numeric inputs. Furthermore, we found that generating additional synthetic training data for the samples with numeric input can increase the input generation accuracy, however this only works when the numbers are integers and only cover a small range.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lorincz-etal-2022-transfer">
<titleInfo>
<title>Transfer learning for multilingual vacancy text generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Lorincz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Graus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dor</namePart>
<namePart type="family">Lavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joao</namePart>
<namePart type="given">Lebre</namePart>
<namePart type="given">Magalhaes</namePart>
<namePart type="family">Pereira</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 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Writing job vacancies is a repetitive and expensive task for humans. This research focuses on automatically generating the benefit sections of vacancies at redacted from job attributes using mT5, the multilingual version of the state-of-the-art T5 transformer trained on general domains to generate texts in multiple languages. While transformers are accurate at generating coherent text, they are sometimes incorrect at including the structured data (the input) in the generated text. Including the input correctly is crucial for vacancy text generation; otherwise, the candidates may get misled. To evaluate how the model includes the input we developed our own domain-specific metrics (input generation accuracy). This was necessary, because Relation Generation, the pre-existing evaluation metric for data-to-text generation uses only string matching, which was not suitable for our dataset (due to the binary field). With the help of the new evaluation method we were able to measure how well the input is included in the generated text separately for different types of inputs (binary, categorical, numeric), offering another contribution to the field. Additionally, we also evaluated how accurate the mT5 model generates the text in the requested language. The results show that mT5 is very accurate at generating the text in the correct language, at including seen categorical inputs and binary values correctly in the generated text. However, mT5 performed worse when generating text from unseen city names or working with numeric inputs. Furthermore, we found that generating additional synthetic training data for the samples with numeric input can increase the input generation accuracy, however this only works when the numbers are integers and only cover a small range.</abstract>
<identifier type="citekey">lorincz-etal-2022-transfer</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.18</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.18</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>207</start>
<end>222</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transfer learning for multilingual vacancy text generation
%A Lorincz, Anna
%A Graus, David
%A Lavi, Dor
%A Pereira, Joao Lebre Magalhaes
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F lorincz-etal-2022-transfer
%X Writing job vacancies is a repetitive and expensive task for humans. This research focuses on automatically generating the benefit sections of vacancies at redacted from job attributes using mT5, the multilingual version of the state-of-the-art T5 transformer trained on general domains to generate texts in multiple languages. While transformers are accurate at generating coherent text, they are sometimes incorrect at including the structured data (the input) in the generated text. Including the input correctly is crucial for vacancy text generation; otherwise, the candidates may get misled. To evaluate how the model includes the input we developed our own domain-specific metrics (input generation accuracy). This was necessary, because Relation Generation, the pre-existing evaluation metric for data-to-text generation uses only string matching, which was not suitable for our dataset (due to the binary field). With the help of the new evaluation method we were able to measure how well the input is included in the generated text separately for different types of inputs (binary, categorical, numeric), offering another contribution to the field. Additionally, we also evaluated how accurate the mT5 model generates the text in the requested language. The results show that mT5 is very accurate at generating the text in the correct language, at including seen categorical inputs and binary values correctly in the generated text. However, mT5 performed worse when generating text from unseen city names or working with numeric inputs. Furthermore, we found that generating additional synthetic training data for the samples with numeric input can increase the input generation accuracy, however this only works when the numbers are integers and only cover a small range.
%R 10.18653/v1/2022.gem-1.18
%U https://aclanthology.org/2022.gem-1.18
%U https://doi.org/10.18653/v1/2022.gem-1.18
%P 207-222
Markdown (Informal)
[Transfer learning for multilingual vacancy text generation](https://aclanthology.org/2022.gem-1.18) (Lorincz et al., GEM 2022)
ACL
- Anna Lorincz, David Graus, Dor Lavi, and Joao Lebre Magalhaes Pereira. 2022. Transfer learning for multilingual vacancy text generation. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 207–222, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.