@inproceedings{leonandya-etal-2019-fast,
title = "The Fast and the Flexible: Training Neural Networks to Learn to Follow Instructions from Small Data",
author = "Leonandya, Rezka and
Hupkes, Dieuwke and
Bruni, Elia and
Kruszewski, Germ{\'a}n",
editor = "Dobnik, Simon and
Chatzikyriakidis, Stergios and
Demberg, Vera",
booktitle = "Proceedings of the 13th International Conference on Computational Semantics - Long Papers",
month = may,
year = "2019",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-0419",
doi = "10.18653/v1/W19-0419",
pages = "223--234",
abstract = "Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is assumed while relying only on a handful of examples to learn from. Work in the past has relied on hand-coded components or manually engineered features to provide strong inductive biases that make learning in such situations possible. In contrast, here we seek to establish whether this knowledge can be acquired automatically by a neural network system through a two phase training procedure: A (slow) offline learning stage where the network learns about the general structure of the task and a (fast) online adaptation phase where the network learns the language of a new given speaker. Controlled experiments show that when the network is exposed to familiar instructions but containing novel words, the model adapts very efficiently to the new vocabulary. Moreover, even for human speakers whose language usage can depart significantly from our artificial training language, our network can still make use of its automatically acquired inductive bias to learn to follow instructions more effectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leonandya-etal-2019-fast">
<titleInfo>
<title>The Fast and the Flexible: Training Neural Networks to Learn to Follow Instructions from Small Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rezka</namePart>
<namePart type="family">Leonandya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elia</namePart>
<namePart type="family">Bruni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Germán</namePart>
<namePart type="family">Kruszewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Conference on Computational Semantics - Long Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stergios</namePart>
<namePart type="family">Chatzikyriakidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is assumed while relying only on a handful of examples to learn from. Work in the past has relied on hand-coded components or manually engineered features to provide strong inductive biases that make learning in such situations possible. In contrast, here we seek to establish whether this knowledge can be acquired automatically by a neural network system through a two phase training procedure: A (slow) offline learning stage where the network learns about the general structure of the task and a (fast) online adaptation phase where the network learns the language of a new given speaker. Controlled experiments show that when the network is exposed to familiar instructions but containing novel words, the model adapts very efficiently to the new vocabulary. Moreover, even for human speakers whose language usage can depart significantly from our artificial training language, our network can still make use of its automatically acquired inductive bias to learn to follow instructions more effectively.</abstract>
<identifier type="citekey">leonandya-etal-2019-fast</identifier>
<identifier type="doi">10.18653/v1/W19-0419</identifier>
<location>
<url>https://aclanthology.org/W19-0419</url>
</location>
<part>
<date>2019-05</date>
<extent unit="page">
<start>223</start>
<end>234</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Fast and the Flexible: Training Neural Networks to Learn to Follow Instructions from Small Data
%A Leonandya, Rezka
%A Hupkes, Dieuwke
%A Bruni, Elia
%A Kruszewski, Germán
%Y Dobnik, Simon
%Y Chatzikyriakidis, Stergios
%Y Demberg, Vera
%S Proceedings of the 13th International Conference on Computational Semantics - Long Papers
%D 2019
%8 May
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F leonandya-etal-2019-fast
%X Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is assumed while relying only on a handful of examples to learn from. Work in the past has relied on hand-coded components or manually engineered features to provide strong inductive biases that make learning in such situations possible. In contrast, here we seek to establish whether this knowledge can be acquired automatically by a neural network system through a two phase training procedure: A (slow) offline learning stage where the network learns about the general structure of the task and a (fast) online adaptation phase where the network learns the language of a new given speaker. Controlled experiments show that when the network is exposed to familiar instructions but containing novel words, the model adapts very efficiently to the new vocabulary. Moreover, even for human speakers whose language usage can depart significantly from our artificial training language, our network can still make use of its automatically acquired inductive bias to learn to follow instructions more effectively.
%R 10.18653/v1/W19-0419
%U https://aclanthology.org/W19-0419
%U https://doi.org/10.18653/v1/W19-0419
%P 223-234
Markdown (Informal)
[The Fast and the Flexible: Training Neural Networks to Learn to Follow Instructions from Small Data](https://aclanthology.org/W19-0419) (Leonandya et al., IWCS 2019)
ACL