@inproceedings{heaton-mitra-2024-deriving,
title = "Deriving Entity-Specific Embeddings from Multi-Entity Sequences",
author = "Heaton, Connor and
Mitra, Prasenjit",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.418",
pages = "4675--4684",
abstract = "Underpinning much of the recent progress in deep learning is the transformer architecture, which takes as input a sequence of embeddings E and emits an updated sequence of embeddings E{'}. A special [CLS] embedding is often included in this sequence, serving as a description of the sequence once processed and used as the basis for subsequent sequence-level tasks. The processed [CLS] embedding loses utility, however, when the model is presented with a multi-entity sequence and asked to perform an entity-specific task. When processing a multi-speaker dialogue, for example, the [CLS] embedding describes the entire dialogue, not any individual utterance/speaker. Existing methods toward entity-specific prediction involve redundant computation or post-processing outside of the transformer. We present a novel methodology for deriving entity-specific embeddings from a multi-entity sequence completely within the transformer, with a loose definition of entity amenable to many problem spaces. To show the generic applicability of our method, we apply it to widely different tasks: emotion recognition in conversation and player performance projection in baseball and show that it can be used to achieve SOTA in both. Code can be found at https://github.com/c-heat16/EntitySpecificEmbeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heaton-mitra-2024-deriving">
<titleInfo>
<title>Deriving Entity-Specific Embeddings from Multi-Entity Sequences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Connor</namePart>
<namePart type="family">Heaton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasenjit</namePart>
<namePart type="family">Mitra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Underpinning much of the recent progress in deep learning is the transformer architecture, which takes as input a sequence of embeddings E and emits an updated sequence of embeddings E’. A special [CLS] embedding is often included in this sequence, serving as a description of the sequence once processed and used as the basis for subsequent sequence-level tasks. The processed [CLS] embedding loses utility, however, when the model is presented with a multi-entity sequence and asked to perform an entity-specific task. When processing a multi-speaker dialogue, for example, the [CLS] embedding describes the entire dialogue, not any individual utterance/speaker. Existing methods toward entity-specific prediction involve redundant computation or post-processing outside of the transformer. We present a novel methodology for deriving entity-specific embeddings from a multi-entity sequence completely within the transformer, with a loose definition of entity amenable to many problem spaces. To show the generic applicability of our method, we apply it to widely different tasks: emotion recognition in conversation and player performance projection in baseball and show that it can be used to achieve SOTA in both. Code can be found at https://github.com/c-heat16/EntitySpecificEmbeddings.</abstract>
<identifier type="citekey">heaton-mitra-2024-deriving</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.418</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4675</start>
<end>4684</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deriving Entity-Specific Embeddings from Multi-Entity Sequences
%A Heaton, Connor
%A Mitra, Prasenjit
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F heaton-mitra-2024-deriving
%X Underpinning much of the recent progress in deep learning is the transformer architecture, which takes as input a sequence of embeddings E and emits an updated sequence of embeddings E’. A special [CLS] embedding is often included in this sequence, serving as a description of the sequence once processed and used as the basis for subsequent sequence-level tasks. The processed [CLS] embedding loses utility, however, when the model is presented with a multi-entity sequence and asked to perform an entity-specific task. When processing a multi-speaker dialogue, for example, the [CLS] embedding describes the entire dialogue, not any individual utterance/speaker. Existing methods toward entity-specific prediction involve redundant computation or post-processing outside of the transformer. We present a novel methodology for deriving entity-specific embeddings from a multi-entity sequence completely within the transformer, with a loose definition of entity amenable to many problem spaces. To show the generic applicability of our method, we apply it to widely different tasks: emotion recognition in conversation and player performance projection in baseball and show that it can be used to achieve SOTA in both. Code can be found at https://github.com/c-heat16/EntitySpecificEmbeddings.
%U https://aclanthology.org/2024.lrec-main.418
%P 4675-4684
Markdown (Informal)
[Deriving Entity-Specific Embeddings from Multi-Entity Sequences](https://aclanthology.org/2024.lrec-main.418) (Heaton & Mitra, LREC-COLING 2024)
ACL