@inproceedings{theodoropoulos-etal-2021-imposing,
title = "Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning",
author = "Theodoropoulos, Christos and
Henderson, James and
Coman, Andrei Catalin and
Moens, Marie-Francine",
editor = "Bisazza, Arianna and
Abend, Omri",
booktitle = "Proceedings of the 25th Conference on Computational Natural Language Learning",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.conll-1.27",
doi = "10.18653/v1/2021.conll-1.27",
pages = "337--348",
abstract = "Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. Given a sentence (unstructured text) and its graph, we use contrastive learning to impose relation-related structure on the token level representations of the sentence obtained with a CharacterBERT (El Boukkouri et al., 2020) model. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task using only a simple KNN classifier, thereby demonstrating the success of the proposed method. Additional visualization by a tSNE analysis shows the effectiveness of the learned representation space compared to baselines. Furthermore, we show that we can learn a different space for named entity recognition, again using a contrastive learning objective, and demonstrate how to successfully combine both representation spaces in an entity-relation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="theodoropoulos-etal-2021-imposing">
<titleInfo>
<title>Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Theodoropoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Henderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="given">Catalin</namePart>
<namePart type="family">Coman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</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 25th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. Given a sentence (unstructured text) and its graph, we use contrastive learning to impose relation-related structure on the token level representations of the sentence obtained with a CharacterBERT (El Boukkouri et al., 2020) model. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task using only a simple KNN classifier, thereby demonstrating the success of the proposed method. Additional visualization by a tSNE analysis shows the effectiveness of the learned representation space compared to baselines. Furthermore, we show that we can learn a different space for named entity recognition, again using a contrastive learning objective, and demonstrate how to successfully combine both representation spaces in an entity-relation task.</abstract>
<identifier type="citekey">theodoropoulos-etal-2021-imposing</identifier>
<identifier type="doi">10.18653/v1/2021.conll-1.27</identifier>
<location>
<url>https://aclanthology.org/2021.conll-1.27</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>337</start>
<end>348</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning
%A Theodoropoulos, Christos
%A Henderson, James
%A Coman, Andrei Catalin
%A Moens, Marie-Francine
%Y Bisazza, Arianna
%Y Abend, Omri
%S Proceedings of the 25th Conference on Computational Natural Language Learning
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F theodoropoulos-etal-2021-imposing
%X Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. Given a sentence (unstructured text) and its graph, we use contrastive learning to impose relation-related structure on the token level representations of the sentence obtained with a CharacterBERT (El Boukkouri et al., 2020) model. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task using only a simple KNN classifier, thereby demonstrating the success of the proposed method. Additional visualization by a tSNE analysis shows the effectiveness of the learned representation space compared to baselines. Furthermore, we show that we can learn a different space for named entity recognition, again using a contrastive learning objective, and demonstrate how to successfully combine both representation spaces in an entity-relation task.
%R 10.18653/v1/2021.conll-1.27
%U https://aclanthology.org/2021.conll-1.27
%U https://doi.org/10.18653/v1/2021.conll-1.27
%P 337-348
Markdown (Informal)
[Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning](https://aclanthology.org/2021.conll-1.27) (Theodoropoulos et al., CoNLL 2021)
ACL