@inproceedings{akula-garibay-2022-sentence,
title = "Sentence Pair Embeddings Based Evaluation Metric for Abstractive and Extractive Summarization",
author = "Akula, Ramya and
Garibay, Ivan",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.646/",
pages = "6009--6017",
abstract = "The development of an automatic evaluation metric remains an open problem in text generation. Widely used evaluation metrics, like ROUGE and BLEU, are based on exact word matching and fail to capture semantic similarity. Recent works, such as BERTScore, MoverScore and, Sentence Mover`s Similarity, are an improvement over these standard metrics as they use the contextualized word or sentence embeddings to capture semantic similarity. We in this work, propose a novel evaluation metric, Sentence Pair EmbEDdings (SPEED) Score, for text generation which is based on semantic similarity between sentence pairs as opposed to earlier approaches. To find semantic similarity between a pair of sentences, we obtain sentence-level embeddings from multiple transformer models pre-trained specifically on various sentence pair tasks such as Paraphrase Detection (PD), Semantic Text Similarity (STS), and Natural Language Inference (NLI). As these sentence pair tasks involve capturing the semantic similarity between a pair of input texts, we leverage these models in our metric computation. Our proposed evaluation metric shows an impressive performance in evaluating both abstractive and extractive summarization models and achieves state-of-the-art results on the SummEval dataset, demonstrating the effectiveness of our approach. Also, we perform the run-time analysis to show that our proposed metric is faster than the current state-of-the-art."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akula-garibay-2022-sentence">
<titleInfo>
<title>Sentence Pair Embeddings Based Evaluation Metric for Abstractive and Extractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramya</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Garibay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of an automatic evaluation metric remains an open problem in text generation. Widely used evaluation metrics, like ROUGE and BLEU, are based on exact word matching and fail to capture semantic similarity. Recent works, such as BERTScore, MoverScore and, Sentence Mover‘s Similarity, are an improvement over these standard metrics as they use the contextualized word or sentence embeddings to capture semantic similarity. We in this work, propose a novel evaluation metric, Sentence Pair EmbEDdings (SPEED) Score, for text generation which is based on semantic similarity between sentence pairs as opposed to earlier approaches. To find semantic similarity between a pair of sentences, we obtain sentence-level embeddings from multiple transformer models pre-trained specifically on various sentence pair tasks such as Paraphrase Detection (PD), Semantic Text Similarity (STS), and Natural Language Inference (NLI). As these sentence pair tasks involve capturing the semantic similarity between a pair of input texts, we leverage these models in our metric computation. Our proposed evaluation metric shows an impressive performance in evaluating both abstractive and extractive summarization models and achieves state-of-the-art results on the SummEval dataset, demonstrating the effectiveness of our approach. Also, we perform the run-time analysis to show that our proposed metric is faster than the current state-of-the-art.</abstract>
<identifier type="citekey">akula-garibay-2022-sentence</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.646/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6009</start>
<end>6017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence Pair Embeddings Based Evaluation Metric for Abstractive and Extractive Summarization
%A Akula, Ramya
%A Garibay, Ivan
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F akula-garibay-2022-sentence
%X The development of an automatic evaluation metric remains an open problem in text generation. Widely used evaluation metrics, like ROUGE and BLEU, are based on exact word matching and fail to capture semantic similarity. Recent works, such as BERTScore, MoverScore and, Sentence Mover‘s Similarity, are an improvement over these standard metrics as they use the contextualized word or sentence embeddings to capture semantic similarity. We in this work, propose a novel evaluation metric, Sentence Pair EmbEDdings (SPEED) Score, for text generation which is based on semantic similarity between sentence pairs as opposed to earlier approaches. To find semantic similarity between a pair of sentences, we obtain sentence-level embeddings from multiple transformer models pre-trained specifically on various sentence pair tasks such as Paraphrase Detection (PD), Semantic Text Similarity (STS), and Natural Language Inference (NLI). As these sentence pair tasks involve capturing the semantic similarity between a pair of input texts, we leverage these models in our metric computation. Our proposed evaluation metric shows an impressive performance in evaluating both abstractive and extractive summarization models and achieves state-of-the-art results on the SummEval dataset, demonstrating the effectiveness of our approach. Also, we perform the run-time analysis to show that our proposed metric is faster than the current state-of-the-art.
%U https://aclanthology.org/2022.lrec-1.646/
%P 6009-6017
Markdown (Informal)
[Sentence Pair Embeddings Based Evaluation Metric for Abstractive and Extractive Summarization](https://aclanthology.org/2022.lrec-1.646/) (Akula & Garibay, LREC 2022)
ACL