@inproceedings{opitz-frank-2022-sbert,
title = "{SBERT} studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features",
author = "Opitz, Juri and
Frank, Anette",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-main.48",
doi = "10.18653/v1/2022.aacl-main.48",
pages = "625--638",
abstract = "Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph metrics for graph-based meaning representations (e.g., Abstract Meaning Representation, AMR) can make explicit the semantic aspects in which two sentences are similar. However, such metrics tend to be slow, rely on parsers, and do not reach state-of-the-art performance when rating sentence similarity. In this work, we aim at the best of both worlds, by learning to induce Semantically Structured Sentence BERT embeddings (S$^3$BERT). Our S$^3$BERT embeddings are composed of explainable sub-embeddings that emphasize various sentence meaning features (e.g., semantic roles, negation, or quantification). We show how to i) learn a decomposition of the sentence embeddings into meaning features, through approximation of a suite of interpretable semantic AMR graph metrics, and how to ii) preserve the overall power of the neural embeddings by controlling the decomposition learning process with a second objective that enforces consistency with the similarity ratings of an SBERT teacher model. In our experimental studies, we show that our approach offers interpretability {--} while preserving the effectiveness and efficiency of the neural sentence embeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="opitz-frank-2022-sbert">
<titleInfo>
<title>SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juri</namePart>
<namePart type="family">Opitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anette</namePart>
<namePart type="family">Frank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph metrics for graph-based meaning representations (e.g., Abstract Meaning Representation, AMR) can make explicit the semantic aspects in which two sentences are similar. However, such metrics tend to be slow, rely on parsers, and do not reach state-of-the-art performance when rating sentence similarity. In this work, we aim at the best of both worlds, by learning to induce Semantically Structured Sentence BERT embeddings (S³BERT). Our S³BERT embeddings are composed of explainable sub-embeddings that emphasize various sentence meaning features (e.g., semantic roles, negation, or quantification). We show how to i) learn a decomposition of the sentence embeddings into meaning features, through approximation of a suite of interpretable semantic AMR graph metrics, and how to ii) preserve the overall power of the neural embeddings by controlling the decomposition learning process with a second objective that enforces consistency with the similarity ratings of an SBERT teacher model. In our experimental studies, we show that our approach offers interpretability – while preserving the effectiveness and efficiency of the neural sentence embeddings.</abstract>
<identifier type="citekey">opitz-frank-2022-sbert</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-main.48</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-main.48</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>625</start>
<end>638</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features
%A Opitz, Juri
%A Frank, Anette
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F opitz-frank-2022-sbert
%X Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph metrics for graph-based meaning representations (e.g., Abstract Meaning Representation, AMR) can make explicit the semantic aspects in which two sentences are similar. However, such metrics tend to be slow, rely on parsers, and do not reach state-of-the-art performance when rating sentence similarity. In this work, we aim at the best of both worlds, by learning to induce Semantically Structured Sentence BERT embeddings (S³BERT). Our S³BERT embeddings are composed of explainable sub-embeddings that emphasize various sentence meaning features (e.g., semantic roles, negation, or quantification). We show how to i) learn a decomposition of the sentence embeddings into meaning features, through approximation of a suite of interpretable semantic AMR graph metrics, and how to ii) preserve the overall power of the neural embeddings by controlling the decomposition learning process with a second objective that enforces consistency with the similarity ratings of an SBERT teacher model. In our experimental studies, we show that our approach offers interpretability – while preserving the effectiveness and efficiency of the neural sentence embeddings.
%R 10.18653/v1/2022.aacl-main.48
%U https://aclanthology.org/2022.aacl-main.48
%U https://doi.org/10.18653/v1/2022.aacl-main.48
%P 625-638
Markdown (Informal)
[SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://aclanthology.org/2022.aacl-main.48) (Opitz & Frank, AACL-IJCNLP 2022)
ACL