@inproceedings{mehta-etal-2020-retouchdown,
title = "Retouchdown: Releasing Touchdown on {S}treet{L}earn as a Public Resource for Language Grounding Tasks in Street View",
author = "Mehta, Harsh and
Artzi, Yoav and
Baldridge, Jason and
Ie, Eugene and
Mirowski, Piotr",
editor = "Kordjamshidi, Parisa and
Bhatia, Archna and
Alikhani, Malihe and
Baldridge, Jason and
Bansal, Mohit and
Moens, Marie-Francine",
booktitle = "Proceedings of the Third International Workshop on Spatial Language Understanding",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.splu-1.7",
doi = "10.18653/v1/2020.splu-1.7",
pages = "56--62",
abstract = "The Touchdown dataset (Chen et al., 2019) provides instructions by human annotators for navigation through New York City streets and for resolving spatial descriptions at a given location. To enable the wider research community to work effectively with the Touchdown tasks, we are publicly releasing the 29k raw Street View panoramas needed for Touchdown. We follow the process used for the StreetLearn data release (Mirowski et al., 2019) to check panoramas for personally identifiable information and blur them as necessary. These have been added to the StreetLearn dataset and can be obtained via the same process as used previously for StreetLearn. We also provide a reference implementation for both Touchdown tasks: vision and language navigation (VLN) and spatial description resolution (SDR). We compare our model results to those given in (Chen et al., 2019) and show that the panoramas we have added to StreetLearn support both Touchdown tasks and can be used effectively for further research and comparison.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehta-etal-2020-retouchdown">
<titleInfo>
<title>Retouchdown: Releasing Touchdown on StreetLearn as a Public Resource for Language Grounding Tasks in Street View</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harsh</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Artzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Baldridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Ie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Mirowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third International Workshop on Spatial Language Understanding</title>
</titleInfo>
<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">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Jason</namePart>
<namePart type="family">Baldridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</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>The Touchdown dataset (Chen et al., 2019) provides instructions by human annotators for navigation through New York City streets and for resolving spatial descriptions at a given location. To enable the wider research community to work effectively with the Touchdown tasks, we are publicly releasing the 29k raw Street View panoramas needed for Touchdown. We follow the process used for the StreetLearn data release (Mirowski et al., 2019) to check panoramas for personally identifiable information and blur them as necessary. These have been added to the StreetLearn dataset and can be obtained via the same process as used previously for StreetLearn. We also provide a reference implementation for both Touchdown tasks: vision and language navigation (VLN) and spatial description resolution (SDR). We compare our model results to those given in (Chen et al., 2019) and show that the panoramas we have added to StreetLearn support both Touchdown tasks and can be used effectively for further research and comparison.</abstract>
<identifier type="citekey">mehta-etal-2020-retouchdown</identifier>
<identifier type="doi">10.18653/v1/2020.splu-1.7</identifier>
<location>
<url>https://aclanthology.org/2020.splu-1.7</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>56</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retouchdown: Releasing Touchdown on StreetLearn as a Public Resource for Language Grounding Tasks in Street View
%A Mehta, Harsh
%A Artzi, Yoav
%A Baldridge, Jason
%A Ie, Eugene
%A Mirowski, Piotr
%Y Kordjamshidi, Parisa
%Y Bhatia, Archna
%Y Alikhani, Malihe
%Y Baldridge, Jason
%Y Bansal, Mohit
%Y Moens, Marie-Francine
%S Proceedings of the Third International Workshop on Spatial Language Understanding
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F mehta-etal-2020-retouchdown
%X The Touchdown dataset (Chen et al., 2019) provides instructions by human annotators for navigation through New York City streets and for resolving spatial descriptions at a given location. To enable the wider research community to work effectively with the Touchdown tasks, we are publicly releasing the 29k raw Street View panoramas needed for Touchdown. We follow the process used for the StreetLearn data release (Mirowski et al., 2019) to check panoramas for personally identifiable information and blur them as necessary. These have been added to the StreetLearn dataset and can be obtained via the same process as used previously for StreetLearn. We also provide a reference implementation for both Touchdown tasks: vision and language navigation (VLN) and spatial description resolution (SDR). We compare our model results to those given in (Chen et al., 2019) and show that the panoramas we have added to StreetLearn support both Touchdown tasks and can be used effectively for further research and comparison.
%R 10.18653/v1/2020.splu-1.7
%U https://aclanthology.org/2020.splu-1.7
%U https://doi.org/10.18653/v1/2020.splu-1.7
%P 56-62
Markdown (Informal)
[Retouchdown: Releasing Touchdown on StreetLearn as a Public Resource for Language Grounding Tasks in Street View](https://aclanthology.org/2020.splu-1.7) (Mehta et al., SpLU 2020)
ACL