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 -