@article{fan-etal-2021-augmenting,
title = "Augmenting Transformers with {KNN}-Based Composite Memory for Dialog",
author = "Fan, Angela and
Gardent, Claire and
Braud, Chlo{\'e} and
Bordes, Antoine",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "9",
year = "2021",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2021.tacl-1.6",
doi = "10.1162/tacl_a_00356",
pages = "82--99",
abstract = "Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) modules. Each KIF module learns a read operation to access fixed external knowledge. We apply these modules to generative dialog modeling, a challenging task where information must be flexibly retrieved and incorporated to maintain the topic and flow of conversation. We demonstrate the effectiveness of our approach by identifying relevant knowledge required for knowledgeable but engaging dialog from Wikipedia, images, and human-written dialog utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2021-augmenting">
<titleInfo>
<title>Augmenting Transformers with KNN-Based Composite Memory for Dialog</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Gardent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloé</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bordes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) modules. Each KIF module learns a read operation to access fixed external knowledge. We apply these modules to generative dialog modeling, a challenging task where information must be flexibly retrieved and incorporated to maintain the topic and flow of conversation. We demonstrate the effectiveness of our approach by identifying relevant knowledge required for knowledgeable but engaging dialog from Wikipedia, images, and human-written dialog utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.</abstract>
<identifier type="citekey">fan-etal-2021-augmenting</identifier>
<identifier type="doi">10.1162/tacl_a_00356</identifier>
<location>
<url>https://aclanthology.org/2021.tacl-1.6</url>
</location>
<part>
<date>2021</date>
<detail type="volume"><number>9</number></detail>
<extent unit="page">
<start>82</start>
<end>99</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Augmenting Transformers with KNN-Based Composite Memory for Dialog
%A Fan, Angela
%A Gardent, Claire
%A Braud, Chloé
%A Bordes, Antoine
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F fan-etal-2021-augmenting
%X Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) modules. Each KIF module learns a read operation to access fixed external knowledge. We apply these modules to generative dialog modeling, a challenging task where information must be flexibly retrieved and incorporated to maintain the topic and flow of conversation. We demonstrate the effectiveness of our approach by identifying relevant knowledge required for knowledgeable but engaging dialog from Wikipedia, images, and human-written dialog utterances, and show that leveraging this retrieved information improves model performance, measured by automatic and human evaluation.
%R 10.1162/tacl_a_00356
%U https://aclanthology.org/2021.tacl-1.6
%U https://doi.org/10.1162/tacl_a_00356
%P 82-99
Markdown (Informal)
[Augmenting Transformers with KNN-Based Composite Memory for Dialog](https://aclanthology.org/2021.tacl-1.6) (Fan et al., TACL 2021)
ACL