@inproceedings{xie-etal-2024-chunk,
title = "Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers",
author = "Xie, Jiawen and
Cheng, Pengyu and
Liang, Xiao and
Dai, Yong and
Du, Nan",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.729",
pages = "13500--13519",
abstract = "Although dominant in natural language processing, transformer-based models still struggle with long-sequence processing, due to the computational costs of their self-attention operations, which increase exponentially as the length of the input sequence grows. To address this challenge, we propose a **Sim**ple framework to enhance the long-content processing of off-the-shelf pre-trained transformers via three steps: **C**hunk, **A**lign, and **S**elect (SimCAS). More specifically, we first divide each long-sequence input into a batch of chunks, then align the inter-chunk information during the encoding steps, and finally, select the most representative hidden states from the encoder for the decoding process. With our SimCAS, the computation and memory costs can be reduced to linear complexity. In experiments, we demonstrate the effectiveness of the proposed method on various real-world long-text summarization and reading comprehension tasks, in which SimCAS significantly outperforms prior long-sequence processing baselines. The code is at [https://github.com/xjw-nlp/SimCAS](https://github.com/xjw-nlp/SimCAS).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2024-chunk">
<titleInfo>
<title>Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiawen</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengyu</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although dominant in natural language processing, transformer-based models still struggle with long-sequence processing, due to the computational costs of their self-attention operations, which increase exponentially as the length of the input sequence grows. To address this challenge, we propose a **Sim**ple framework to enhance the long-content processing of off-the-shelf pre-trained transformers via three steps: **C**hunk, **A**lign, and **S**elect (SimCAS). More specifically, we first divide each long-sequence input into a batch of chunks, then align the inter-chunk information during the encoding steps, and finally, select the most representative hidden states from the encoder for the decoding process. With our SimCAS, the computation and memory costs can be reduced to linear complexity. In experiments, we demonstrate the effectiveness of the proposed method on various real-world long-text summarization and reading comprehension tasks, in which SimCAS significantly outperforms prior long-sequence processing baselines. The code is at [https://github.com/xjw-nlp/SimCAS](https://github.com/xjw-nlp/SimCAS).</abstract>
<identifier type="citekey">xie-etal-2024-chunk</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.729</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13500</start>
<end>13519</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers
%A Xie, Jiawen
%A Cheng, Pengyu
%A Liang, Xiao
%A Dai, Yong
%A Du, Nan
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F xie-etal-2024-chunk
%X Although dominant in natural language processing, transformer-based models still struggle with long-sequence processing, due to the computational costs of their self-attention operations, which increase exponentially as the length of the input sequence grows. To address this challenge, we propose a **Sim**ple framework to enhance the long-content processing of off-the-shelf pre-trained transformers via three steps: **C**hunk, **A**lign, and **S**elect (SimCAS). More specifically, we first divide each long-sequence input into a batch of chunks, then align the inter-chunk information during the encoding steps, and finally, select the most representative hidden states from the encoder for the decoding process. With our SimCAS, the computation and memory costs can be reduced to linear complexity. In experiments, we demonstrate the effectiveness of the proposed method on various real-world long-text summarization and reading comprehension tasks, in which SimCAS significantly outperforms prior long-sequence processing baselines. The code is at [https://github.com/xjw-nlp/SimCAS](https://github.com/xjw-nlp/SimCAS).
%U https://aclanthology.org/2024.acl-long.729
%P 13500-13519
Markdown (Informal)
[Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers](https://aclanthology.org/2024.acl-long.729) (Xie et al., ACL 2024)
ACL