@inproceedings{garneau-lamontagne-2021-trainable,
title = "Trainable Ranking Models to Evaluate the Semantic Accuracy of Data-to-Text Neural Generator",
author = "Garneau, Nicolas and
Lamontagne, Luc",
editor = "Gao, Yang and
Eger, Steffen and
Zhao, Wei and
Lertvittayakumjorn, Piyawat and
Fomicheva, Marina",
booktitle = "Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eval4nlp-1.6",
doi = "10.18653/v1/2021.eval4nlp-1.6",
pages = "51--61",
abstract = "In this paper, we introduce a new embedding-based metric relying on trainable ranking models to evaluate the semantic accuracy of neural data-to-text generators. This metric is especially well suited to semantically and factually assess the performance of a text generator when tables can be associated with multiple references and table values contain textual utterances. We first present how one can implement and further specialize the metric by training the underlying ranking models on a legal Data-to-Text dataset. We show how it may provide a more robust evaluation than other evaluation schemes in challenging settings using a dataset comprising paraphrases between the table values and their respective references. Finally, we evaluate its generalization capabilities on a well-known dataset, WebNLG, by comparing it with human evaluation and a recently introduced metric based on natural language inference. We then illustrate how it naturally characterizes, both quantitatively and qualitatively, omissions and hallucinations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garneau-lamontagne-2021-trainable">
<titleInfo>
<title>Trainable Ranking Models to Evaluate the Semantic Accuracy of Data-to-Text Neural Generator</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Garneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luc</namePart>
<namePart type="family">Lamontagne</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>Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyawat</namePart>
<namePart type="family">Lertvittayakumjorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Fomicheva</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>In this paper, we introduce a new embedding-based metric relying on trainable ranking models to evaluate the semantic accuracy of neural data-to-text generators. This metric is especially well suited to semantically and factually assess the performance of a text generator when tables can be associated with multiple references and table values contain textual utterances. We first present how one can implement and further specialize the metric by training the underlying ranking models on a legal Data-to-Text dataset. We show how it may provide a more robust evaluation than other evaluation schemes in challenging settings using a dataset comprising paraphrases between the table values and their respective references. Finally, we evaluate its generalization capabilities on a well-known dataset, WebNLG, by comparing it with human evaluation and a recently introduced metric based on natural language inference. We then illustrate how it naturally characterizes, both quantitatively and qualitatively, omissions and hallucinations.</abstract>
<identifier type="citekey">garneau-lamontagne-2021-trainable</identifier>
<identifier type="doi">10.18653/v1/2021.eval4nlp-1.6</identifier>
<location>
<url>https://aclanthology.org/2021.eval4nlp-1.6</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>51</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trainable Ranking Models to Evaluate the Semantic Accuracy of Data-to-Text Neural Generator
%A Garneau, Nicolas
%A Lamontagne, Luc
%Y Gao, Yang
%Y Eger, Steffen
%Y Zhao, Wei
%Y Lertvittayakumjorn, Piyawat
%Y Fomicheva, Marina
%S Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F garneau-lamontagne-2021-trainable
%X In this paper, we introduce a new embedding-based metric relying on trainable ranking models to evaluate the semantic accuracy of neural data-to-text generators. This metric is especially well suited to semantically and factually assess the performance of a text generator when tables can be associated with multiple references and table values contain textual utterances. We first present how one can implement and further specialize the metric by training the underlying ranking models on a legal Data-to-Text dataset. We show how it may provide a more robust evaluation than other evaluation schemes in challenging settings using a dataset comprising paraphrases between the table values and their respective references. Finally, we evaluate its generalization capabilities on a well-known dataset, WebNLG, by comparing it with human evaluation and a recently introduced metric based on natural language inference. We then illustrate how it naturally characterizes, both quantitatively and qualitatively, omissions and hallucinations.
%R 10.18653/v1/2021.eval4nlp-1.6
%U https://aclanthology.org/2021.eval4nlp-1.6
%U https://doi.org/10.18653/v1/2021.eval4nlp-1.6
%P 51-61
Markdown (Informal)
[Trainable Ranking Models to Evaluate the Semantic Accuracy of Data-to-Text Neural Generator](https://aclanthology.org/2021.eval4nlp-1.6) (Garneau & Lamontagne, Eval4NLP 2021)
ACL