@inproceedings{katsakioris-etal-2021-learning,
title = "Learning to Read Maps: Understanding Natural Language Instructions from Unseen Maps",
author = "Katsakioris, Miltiadis Marios and
Konstas, Ioannis and
Mignotte, Pierre Yves and
Hastie, Helen",
editor = "Alikhani, Malihe and
Blukis, Valts and
Kordjamshidi, Parisa and
Padmakumar, Aishwarya and
Tan, Hao",
booktitle = "Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.splurobonlp-1.2",
doi = "10.18653/v1/2021.splurobonlp-1.2",
pages = "11--21",
abstract = "Robust situated dialog requires the ability to process instructions based on spatial information, which may or may not be available. We propose a model, based on LXMERT, that can extract spatial information from text instructions and attend to landmarks on OpenStreetMap (OSM) referred to in a natural language instruction. Whilst, OSM is a valuable resource, as with any open-sourced data, there is noise and variation in the names referred to on the map, as well as, variation in natural language instructions, hence the need for data-driven methods over rule-based systems. This paper demonstrates that the gold GPS location can be accurately predicted from the natural language instruction and metadata with 72{\%} accuracy for previously seen maps and 64{\%} for unseen maps.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="katsakioris-etal-2021-learning">
<titleInfo>
<title>Learning to Read Maps: Understanding Natural Language Instructions from Unseen Maps</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miltiadis</namePart>
<namePart type="given">Marios</namePart>
<namePart type="family">Katsakioris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="given">Yves</namePart>
<namePart type="family">Mignotte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Hastie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valts</namePart>
<namePart type="family">Blukis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Robust situated dialog requires the ability to process instructions based on spatial information, which may or may not be available. We propose a model, based on LXMERT, that can extract spatial information from text instructions and attend to landmarks on OpenStreetMap (OSM) referred to in a natural language instruction. Whilst, OSM is a valuable resource, as with any open-sourced data, there is noise and variation in the names referred to on the map, as well as, variation in natural language instructions, hence the need for data-driven methods over rule-based systems. This paper demonstrates that the gold GPS location can be accurately predicted from the natural language instruction and metadata with 72% accuracy for previously seen maps and 64% for unseen maps.</abstract>
<identifier type="citekey">katsakioris-etal-2021-learning</identifier>
<identifier type="doi">10.18653/v1/2021.splurobonlp-1.2</identifier>
<location>
<url>https://aclanthology.org/2021.splurobonlp-1.2</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>11</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Read Maps: Understanding Natural Language Instructions from Unseen Maps
%A Katsakioris, Miltiadis Marios
%A Konstas, Ioannis
%A Mignotte, Pierre Yves
%A Hastie, Helen
%Y Alikhani, Malihe
%Y Blukis, Valts
%Y Kordjamshidi, Parisa
%Y Padmakumar, Aishwarya
%Y Tan, Hao
%S Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F katsakioris-etal-2021-learning
%X Robust situated dialog requires the ability to process instructions based on spatial information, which may or may not be available. We propose a model, based on LXMERT, that can extract spatial information from text instructions and attend to landmarks on OpenStreetMap (OSM) referred to in a natural language instruction. Whilst, OSM is a valuable resource, as with any open-sourced data, there is noise and variation in the names referred to on the map, as well as, variation in natural language instructions, hence the need for data-driven methods over rule-based systems. This paper demonstrates that the gold GPS location can be accurately predicted from the natural language instruction and metadata with 72% accuracy for previously seen maps and 64% for unseen maps.
%R 10.18653/v1/2021.splurobonlp-1.2
%U https://aclanthology.org/2021.splurobonlp-1.2
%U https://doi.org/10.18653/v1/2021.splurobonlp-1.2
%P 11-21
Markdown (Informal)
[Learning to Read Maps: Understanding Natural Language Instructions from Unseen Maps](https://aclanthology.org/2021.splurobonlp-1.2) (Katsakioris et al., splurobonlp 2021)
ACL