@inproceedings{murthy-etal-2023-semi,
title = "Semi-Structured Object Sequence Encoders",
author = "Murthy, Rudra and
Bhat, Riyaz and
Gunasekara, Chulaka and
Patel, Siva and
Wan, Hui and
Dhamecha, Tejas and
Contractor, Danish and
Danilevsky, Marina",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.605",
doi = "10.18653/v1/2023.findings-emnlp.605",
pages = "9026--9039",
abstract = "In this paper we explore the task of modeling semi-structured object sequences; in particular, we focus our attention on the problem of developing a structure-aware input representation for such sequences. Examples of such data include user activity on websites, machine logs, and many others. This type of data is often represented as a sequence of sets of key-value pairs over time and can present modeling challenges due to an ever-increasing sequence length. We propose a two-part approach, which first considers each key independently and encodes a representation of its values over time; we then self-attend over these value-aware key representations to accomplish a downstream task. This allows us to operate on longer object sequences than existing methods. We introduce a novel shared-attention-head architecture between the two modules and present an innovative training schedule that interleaves the training of both modules with shared weights for some attention heads. Our experiments on multiple prediction tasks using real-world data demonstrate that our approach outperforms a unified network with hierarchical encoding, as well as other methods including a \textit{record-centric} representation and a \textit{flattened} representation of the sequence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="murthy-etal-2023-semi">
<titleInfo>
<title>Semi-Structured Object Sequence Encoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rudra</namePart>
<namePart type="family">Murthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riyaz</namePart>
<namePart type="family">Bhat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulaka</namePart>
<namePart type="family">Gunasekara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siva</namePart>
<namePart type="family">Patel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejas</namePart>
<namePart type="family">Dhamecha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danish</namePart>
<namePart type="family">Contractor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Danilevsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we explore the task of modeling semi-structured object sequences; in particular, we focus our attention on the problem of developing a structure-aware input representation for such sequences. Examples of such data include user activity on websites, machine logs, and many others. This type of data is often represented as a sequence of sets of key-value pairs over time and can present modeling challenges due to an ever-increasing sequence length. We propose a two-part approach, which first considers each key independently and encodes a representation of its values over time; we then self-attend over these value-aware key representations to accomplish a downstream task. This allows us to operate on longer object sequences than existing methods. We introduce a novel shared-attention-head architecture between the two modules and present an innovative training schedule that interleaves the training of both modules with shared weights for some attention heads. Our experiments on multiple prediction tasks using real-world data demonstrate that our approach outperforms a unified network with hierarchical encoding, as well as other methods including a record-centric representation and a flattened representation of the sequence.</abstract>
<identifier type="citekey">murthy-etal-2023-semi</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.605</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.605</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>9026</start>
<end>9039</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-Structured Object Sequence Encoders
%A Murthy, Rudra
%A Bhat, Riyaz
%A Gunasekara, Chulaka
%A Patel, Siva
%A Wan, Hui
%A Dhamecha, Tejas
%A Contractor, Danish
%A Danilevsky, Marina
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F murthy-etal-2023-semi
%X In this paper we explore the task of modeling semi-structured object sequences; in particular, we focus our attention on the problem of developing a structure-aware input representation for such sequences. Examples of such data include user activity on websites, machine logs, and many others. This type of data is often represented as a sequence of sets of key-value pairs over time and can present modeling challenges due to an ever-increasing sequence length. We propose a two-part approach, which first considers each key independently and encodes a representation of its values over time; we then self-attend over these value-aware key representations to accomplish a downstream task. This allows us to operate on longer object sequences than existing methods. We introduce a novel shared-attention-head architecture between the two modules and present an innovative training schedule that interleaves the training of both modules with shared weights for some attention heads. Our experiments on multiple prediction tasks using real-world data demonstrate that our approach outperforms a unified network with hierarchical encoding, as well as other methods including a record-centric representation and a flattened representation of the sequence.
%R 10.18653/v1/2023.findings-emnlp.605
%U https://aclanthology.org/2023.findings-emnlp.605
%U https://doi.org/10.18653/v1/2023.findings-emnlp.605
%P 9026-9039
Markdown (Informal)
[Semi-Structured Object Sequence Encoders](https://aclanthology.org/2023.findings-emnlp.605) (Murthy et al., Findings 2023)
ACL
- Rudra Murthy, Riyaz Bhat, Chulaka Gunasekara, Siva Patel, Hui Wan, Tejas Dhamecha, Danish Contractor, and Marina Danilevsky. 2023. Semi-Structured Object Sequence Encoders. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9026–9039, Singapore. Association for Computational Linguistics.