Embedding and Clustering Multi-Entity Sequences

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Connor Heaton
  • Prasenjit Mitra

Organisationseinheiten

Externe Organisationen

  • Pennsylvania State University
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)57492-57503
Seitenumfang12
FachzeitschriftIEEE ACCESS
Jahrgang12
PublikationsstatusVeröffentlicht - 22 Apr. 2024

Abstract

Core to much of modern deep learning is the notion of representation learning, learning representations of things that are useful for performing some task(s) related to those things. Encoder-only language models, for example, learn representations of language useful for performing language-related tasks, often classification. While fruitful in many applications, inherent is the assumption that only one classification is to be made for a particular input. This poses challenges when multiple classifications are to be made about different portions of a single record, such as emotion recognition in conversation (ERC) where the objective is to classify the emotion in each utterance of a dialog. Existing methods for this task typically either involve redundant computation, non-trivial post-processing outside of the core language model backbone, or both. To address this, we generalize recent work for deriving player-specific embeddings from multi-player sequences of events in sport for domain-agnostic application while also enabling it to leverage inter-entity relationships. Seeing the efficacy of the method in regression and classification tasks, we explore how it can be used to cluster player representations, proposing a novel approach for distribution-aware deep-clustering in the absence of labels. We demonstrate how the proposed methods yield state-of-the-art performance on the disparate tasks of ERC in Natural Language Processing (NLP), long-tail partial-label-learning (LT-PLL) in Computer Vision (CV), and player form clustering in sports analytics.

Zitieren

Embedding and Clustering Multi-Entity Sequences. / Heaton, Connor; Mitra, Prasenjit.
in: IEEE ACCESS, Jahrgang 12, 22.04.2024, S. 57492-57503.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Heaton C, Mitra P. Embedding and Clustering Multi-Entity Sequences. IEEE ACCESS. 2024 Apr 22;12:57492-57503. doi: 10.1109/ACCESS.2024.3391820
Heaton, Connor ; Mitra, Prasenjit. / Embedding and Clustering Multi-Entity Sequences. in: IEEE ACCESS. 2024 ; Jahrgang 12. S. 57492-57503.
Download
@article{8a0bbd940e5b4864baa641b761f0248a,
title = "Embedding and Clustering Multi-Entity Sequences",
abstract = "Core to much of modern deep learning is the notion of representation learning, learning representations of things that are useful for performing some task(s) related to those things. Encoder-only language models, for example, learn representations of language useful for performing language-related tasks, often classification. While fruitful in many applications, inherent is the assumption that only one classification is to be made for a particular input. This poses challenges when multiple classifications are to be made about different portions of a single record, such as emotion recognition in conversation (ERC) where the objective is to classify the emotion in each utterance of a dialog. Existing methods for this task typically either involve redundant computation, non-trivial post-processing outside of the core language model backbone, or both. To address this, we generalize recent work for deriving player-specific embeddings from multi-player sequences of events in sport for domain-agnostic application while also enabling it to leverage inter-entity relationships. Seeing the efficacy of the method in regression and classification tasks, we explore how it can be used to cluster player representations, proposing a novel approach for distribution-aware deep-clustering in the absence of labels. We demonstrate how the proposed methods yield state-of-the-art performance on the disparate tasks of ERC in Natural Language Processing (NLP), long-tail partial-label-learning (LT-PLL) in Computer Vision (CV), and player form clustering in sports analytics.",
keywords = "emotion recognition in conversation, long-tail partial-label-learning, Representation learning, sports analytics",
author = "Connor Heaton and Prasenjit Mitra",
note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",
year = "2024",
month = apr,
day = "22",
doi = "10.1109/ACCESS.2024.3391820",
language = "English",
volume = "12",
pages = "57492--57503",
journal = "IEEE ACCESS",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Download

TY - JOUR

T1 - Embedding and Clustering Multi-Entity Sequences

AU - Heaton, Connor

AU - Mitra, Prasenjit

N1 - Publisher Copyright: © 2013 IEEE.

PY - 2024/4/22

Y1 - 2024/4/22

N2 - Core to much of modern deep learning is the notion of representation learning, learning representations of things that are useful for performing some task(s) related to those things. Encoder-only language models, for example, learn representations of language useful for performing language-related tasks, often classification. While fruitful in many applications, inherent is the assumption that only one classification is to be made for a particular input. This poses challenges when multiple classifications are to be made about different portions of a single record, such as emotion recognition in conversation (ERC) where the objective is to classify the emotion in each utterance of a dialog. Existing methods for this task typically either involve redundant computation, non-trivial post-processing outside of the core language model backbone, or both. To address this, we generalize recent work for deriving player-specific embeddings from multi-player sequences of events in sport for domain-agnostic application while also enabling it to leverage inter-entity relationships. Seeing the efficacy of the method in regression and classification tasks, we explore how it can be used to cluster player representations, proposing a novel approach for distribution-aware deep-clustering in the absence of labels. We demonstrate how the proposed methods yield state-of-the-art performance on the disparate tasks of ERC in Natural Language Processing (NLP), long-tail partial-label-learning (LT-PLL) in Computer Vision (CV), and player form clustering in sports analytics.

AB - Core to much of modern deep learning is the notion of representation learning, learning representations of things that are useful for performing some task(s) related to those things. Encoder-only language models, for example, learn representations of language useful for performing language-related tasks, often classification. While fruitful in many applications, inherent is the assumption that only one classification is to be made for a particular input. This poses challenges when multiple classifications are to be made about different portions of a single record, such as emotion recognition in conversation (ERC) where the objective is to classify the emotion in each utterance of a dialog. Existing methods for this task typically either involve redundant computation, non-trivial post-processing outside of the core language model backbone, or both. To address this, we generalize recent work for deriving player-specific embeddings from multi-player sequences of events in sport for domain-agnostic application while also enabling it to leverage inter-entity relationships. Seeing the efficacy of the method in regression and classification tasks, we explore how it can be used to cluster player representations, proposing a novel approach for distribution-aware deep-clustering in the absence of labels. We demonstrate how the proposed methods yield state-of-the-art performance on the disparate tasks of ERC in Natural Language Processing (NLP), long-tail partial-label-learning (LT-PLL) in Computer Vision (CV), and player form clustering in sports analytics.

KW - emotion recognition in conversation

KW - long-tail partial-label-learning

KW - Representation learning

KW - sports analytics

UR - http://www.scopus.com/inward/record.url?scp=85191342903&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2024.3391820

DO - 10.1109/ACCESS.2024.3391820

M3 - Article

AN - SCOPUS:85191342903

VL - 12

SP - 57492

EP - 57503

JO - IEEE ACCESS

JF - IEEE ACCESS

SN - 2169-3536

ER -