@inproceedings{tseriotou-etal-2023-sequential,
title = "Sequential Path Signature Networks for Personalised Longitudinal Language Modeling",
author = "Tseriotou, Talia and
Tsakalidis, Adam and
Foster, Peter and
Lyons, Terence and
Liakata, Maria",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.310",
doi = "10.18653/v1/2023.findings-acl.310",
pages = "5016--5031",
abstract = "Longitudinal user modeling can provide a strong signal for various downstream tasks. Despite the rapid progress in representation learning, dynamic aspects of modelling individuals{'} language have only been sparsely addressed. We present a novel extension of neural sequential models using the notion of path signatures from rough path theory, which constitute graduated summaries of continuous paths and have the ability to capture non-linearities in trajectories. By combining path signatures of users{'} history with contextual neural representations and recursive neural networks we can produce compact time-sensitive user representations. Given the magnitude of mental health conditions with symptoms manifesting in language, we show the applicability of our approach on the task of identifying changes in individuals{'} mood by analysing their online textual content. By directly integrating signature transforms of users{'} history in the model architecture we jointly address the two most important aspects of the task, namely sequentiality and temporality. Our approach achieves state-of-the-art performance on macro-average F1 score on the two available datasets for the task, outperforming or performing on-par with state-of-the-art models utilising only historical posts and even outperforming prior models which also have access to future posts of users.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tseriotou-etal-2023-sequential">
<titleInfo>
<title>Sequential Path Signature Networks for Personalised Longitudinal Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Talia</namePart>
<namePart type="family">Tseriotou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Tsakalidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terence</namePart>
<namePart type="family">Lyons</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Longitudinal user modeling can provide a strong signal for various downstream tasks. Despite the rapid progress in representation learning, dynamic aspects of modelling individuals’ language have only been sparsely addressed. We present a novel extension of neural sequential models using the notion of path signatures from rough path theory, which constitute graduated summaries of continuous paths and have the ability to capture non-linearities in trajectories. By combining path signatures of users’ history with contextual neural representations and recursive neural networks we can produce compact time-sensitive user representations. Given the magnitude of mental health conditions with symptoms manifesting in language, we show the applicability of our approach on the task of identifying changes in individuals’ mood by analysing their online textual content. By directly integrating signature transforms of users’ history in the model architecture we jointly address the two most important aspects of the task, namely sequentiality and temporality. Our approach achieves state-of-the-art performance on macro-average F1 score on the two available datasets for the task, outperforming or performing on-par with state-of-the-art models utilising only historical posts and even outperforming prior models which also have access to future posts of users.</abstract>
<identifier type="citekey">tseriotou-etal-2023-sequential</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.310</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.310</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5016</start>
<end>5031</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sequential Path Signature Networks for Personalised Longitudinal Language Modeling
%A Tseriotou, Talia
%A Tsakalidis, Adam
%A Foster, Peter
%A Lyons, Terence
%A Liakata, Maria
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tseriotou-etal-2023-sequential
%X Longitudinal user modeling can provide a strong signal for various downstream tasks. Despite the rapid progress in representation learning, dynamic aspects of modelling individuals’ language have only been sparsely addressed. We present a novel extension of neural sequential models using the notion of path signatures from rough path theory, which constitute graduated summaries of continuous paths and have the ability to capture non-linearities in trajectories. By combining path signatures of users’ history with contextual neural representations and recursive neural networks we can produce compact time-sensitive user representations. Given the magnitude of mental health conditions with symptoms manifesting in language, we show the applicability of our approach on the task of identifying changes in individuals’ mood by analysing their online textual content. By directly integrating signature transforms of users’ history in the model architecture we jointly address the two most important aspects of the task, namely sequentiality and temporality. Our approach achieves state-of-the-art performance on macro-average F1 score on the two available datasets for the task, outperforming or performing on-par with state-of-the-art models utilising only historical posts and even outperforming prior models which also have access to future posts of users.
%R 10.18653/v1/2023.findings-acl.310
%U https://aclanthology.org/2023.findings-acl.310
%U https://doi.org/10.18653/v1/2023.findings-acl.310
%P 5016-5031
Markdown (Informal)
[Sequential Path Signature Networks for Personalised Longitudinal Language Modeling](https://aclanthology.org/2023.findings-acl.310) (Tseriotou et al., Findings 2023)
ACL