@inproceedings{paz-argaman-etal-2024-go,
title = "Where Do We Go From Here? Multi-scale Allocentric Relational Inferencefrom Natural Spatial Descriptions",
author = "Paz-Argaman, Tzuf and
Palowitch, John and
Kulkarni, Sayali and
Baldridge, Jason and
Tsarfaty, Reut",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.62",
pages = "1026--1040",
abstract = "The concept of \textit{acquired spatial knowledge} is crucial in spatial cognitive research, particularly when it comes to communicating routes. However, NLP navigation studies often overlook the impact of acquired knowledge on textual descriptions. Current navigation studies concentrate on egocentric local descriptions (e.g., {`}it will be on your right{'}) that require reasoning over the agent{'}s local perception. These instructions are typically given in a sequence of steps, with each action-step explicitly mentioned and followed by a landmark that the agent can use to verify that they are on the correct path (e.g., {`}turn right and then you will see...{'}). In contrast, descriptions based on knowledge acquired through a map provide a complete view of the environment and capture its compositionality. These instructions typically contain allocentric relations, are non-sequential, with implicit actions and multiple spatial relations without any verification (e.g., {`}south of Central Park and a block north of a police station{'}). This paper introduces the Rendezvous (RVS) task and dataset, which includes 10,404 examples of English geospatial instructions for reaching a target location using map-knowledge. Our analysis reveals that RVS exhibits a richer use of spatial allocentric relations, and requires resolving more spatial relations simultaneously compared to previous text-based navigation benchmarks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paz-argaman-etal-2024-go">
<titleInfo>
<title>Where Do We Go From Here? Multi-scale Allocentric Relational Inferencefrom Natural Spatial Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tzuf</namePart>
<namePart type="family">Paz-Argaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Palowitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sayali</namePart>
<namePart type="family">Kulkarni</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">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The concept of acquired spatial knowledge is crucial in spatial cognitive research, particularly when it comes to communicating routes. However, NLP navigation studies often overlook the impact of acquired knowledge on textual descriptions. Current navigation studies concentrate on egocentric local descriptions (e.g., ‘it will be on your right’) that require reasoning over the agent’s local perception. These instructions are typically given in a sequence of steps, with each action-step explicitly mentioned and followed by a landmark that the agent can use to verify that they are on the correct path (e.g., ‘turn right and then you will see...’). In contrast, descriptions based on knowledge acquired through a map provide a complete view of the environment and capture its compositionality. These instructions typically contain allocentric relations, are non-sequential, with implicit actions and multiple spatial relations without any verification (e.g., ‘south of Central Park and a block north of a police station’). This paper introduces the Rendezvous (RVS) task and dataset, which includes 10,404 examples of English geospatial instructions for reaching a target location using map-knowledge. Our analysis reveals that RVS exhibits a richer use of spatial allocentric relations, and requires resolving more spatial relations simultaneously compared to previous text-based navigation benchmarks.</abstract>
<identifier type="citekey">paz-argaman-etal-2024-go</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.62</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1026</start>
<end>1040</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Where Do We Go From Here? Multi-scale Allocentric Relational Inferencefrom Natural Spatial Descriptions
%A Paz-Argaman, Tzuf
%A Palowitch, John
%A Kulkarni, Sayali
%A Baldridge, Jason
%A Tsarfaty, Reut
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F paz-argaman-etal-2024-go
%X The concept of acquired spatial knowledge is crucial in spatial cognitive research, particularly when it comes to communicating routes. However, NLP navigation studies often overlook the impact of acquired knowledge on textual descriptions. Current navigation studies concentrate on egocentric local descriptions (e.g., ‘it will be on your right’) that require reasoning over the agent’s local perception. These instructions are typically given in a sequence of steps, with each action-step explicitly mentioned and followed by a landmark that the agent can use to verify that they are on the correct path (e.g., ‘turn right and then you will see...’). In contrast, descriptions based on knowledge acquired through a map provide a complete view of the environment and capture its compositionality. These instructions typically contain allocentric relations, are non-sequential, with implicit actions and multiple spatial relations without any verification (e.g., ‘south of Central Park and a block north of a police station’). This paper introduces the Rendezvous (RVS) task and dataset, which includes 10,404 examples of English geospatial instructions for reaching a target location using map-knowledge. Our analysis reveals that RVS exhibits a richer use of spatial allocentric relations, and requires resolving more spatial relations simultaneously compared to previous text-based navigation benchmarks.
%U https://aclanthology.org/2024.eacl-long.62
%P 1026-1040
Markdown (Informal)
[Where Do We Go From Here? Multi-scale Allocentric Relational Inferencefrom Natural Spatial Descriptions](https://aclanthology.org/2024.eacl-long.62) (Paz-Argaman et al., EACL 2024)
ACL