@inproceedings{martins-etal-2022-former,
title = "$\infty$-former: Infinite Memory Transformer",
author = "Martins, Pedro Henrique and
Marinho, Zita and
Martins, Andre",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.375",
doi = "10.18653/v1/2022.acl-long.375",
pages = "5468--5485",
abstract = "Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite memory capacity and are forced to drop old information. In this paper, we propose the $\infty$-former, which extends the vanilla transformer with an unbounded long-term memory. By making use of a continuous-space attention mechanism to attend over the long-term memory, the $\infty$-former{'}s attention complexity becomes independent of the context length, trading off memory length with precision.In order to control where precision is more important, $\infty$-former maintains {``}sticky memories,{''} being able to model arbitrarily long contexts while keeping the computation budget fixed.Experiments on a synthetic sorting task, language modeling, and document grounded dialogue generation demonstrate the $\infty$-former{'}s ability to retain information from long sequences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martins-etal-2022-former">
<titleInfo>
<title>ınfty-former: Infinite Memory Transformer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zita</namePart>
<namePart type="family">Marinho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite memory capacity and are forced to drop old information. In this paper, we propose the ınfty-former, which extends the vanilla transformer with an unbounded long-term memory. By making use of a continuous-space attention mechanism to attend over the long-term memory, the ınfty-former’s attention complexity becomes independent of the context length, trading off memory length with precision.In order to control where precision is more important, ınfty-former maintains “sticky memories,” being able to model arbitrarily long contexts while keeping the computation budget fixed.Experiments on a synthetic sorting task, language modeling, and document grounded dialogue generation demonstrate the ınfty-former’s ability to retain information from long sequences.</abstract>
<identifier type="citekey">martins-etal-2022-former</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.375</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.375</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>5468</start>
<end>5485</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ınfty-former: Infinite Memory Transformer
%A Martins, Pedro Henrique
%A Marinho, Zita
%A Martins, Andre
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F martins-etal-2022-former
%X Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite memory capacity and are forced to drop old information. In this paper, we propose the ınfty-former, which extends the vanilla transformer with an unbounded long-term memory. By making use of a continuous-space attention mechanism to attend over the long-term memory, the ınfty-former’s attention complexity becomes independent of the context length, trading off memory length with precision.In order to control where precision is more important, ınfty-former maintains “sticky memories,” being able to model arbitrarily long contexts while keeping the computation budget fixed.Experiments on a synthetic sorting task, language modeling, and document grounded dialogue generation demonstrate the ınfty-former’s ability to retain information from long sequences.
%R 10.18653/v1/2022.acl-long.375
%U https://aclanthology.org/2022.acl-long.375
%U https://doi.org/10.18653/v1/2022.acl-long.375
%P 5468-5485
Markdown (Informal)
[∞-former: Infinite Memory Transformer](https://aclanthology.org/2022.acl-long.375) (Martins et al., ACL 2022)
ACL
- Pedro Henrique Martins, Zita Marinho, and Andre Martins. 2022. ∞-former: Infinite Memory Transformer. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5468–5485, Dublin, Ireland. Association for Computational Linguistics.