@inproceedings{radevski-etal-2020-decoding,
title = "{D}ecoding Language Spatial Relations to 2{D} Spatial Arrangements",
author = "Radevski, Gorjan and
Collell, Guillem and
Moens, Marie-Francine and
Tuytelaars, Tinne",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.408",
doi = "10.18653/v1/2020.findings-emnlp.408",
pages = "4549--4560",
abstract = "We address the problem of multimodal spatial understanding by decoding a set of language-expressed spatial relations to a set of 2D spatial arrangements in a multi-object and multi-relationship setting. We frame the task as arranging a scene of clip-arts given a textual description. We propose a simple and effective model architecture Spatial-Reasoning Bert (SR-Bert), trained to decode text to 2D spatial arrangements in a non-autoregressive manner. SR-Bert can decode both explicit and implicit language to 2D spatial arrangements, generalizes to out-of-sample data to a reasonable extent and can generate complete abstract scenes if paired with a clip-arts predictor. Finally, we qualitatively evaluate our method with a user study, validating that our generated spatial arrangements align with human expectation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="radevski-etal-2020-decoding">
<titleInfo>
<title>Decoding Language Spatial Relations to 2D Spatial Arrangements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gorjan</namePart>
<namePart type="family">Radevski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillem</namePart>
<namePart type="family">Collell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tinne</namePart>
<namePart type="family">Tuytelaars</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>We address the problem of multimodal spatial understanding by decoding a set of language-expressed spatial relations to a set of 2D spatial arrangements in a multi-object and multi-relationship setting. We frame the task as arranging a scene of clip-arts given a textual description. We propose a simple and effective model architecture Spatial-Reasoning Bert (SR-Bert), trained to decode text to 2D spatial arrangements in a non-autoregressive manner. SR-Bert can decode both explicit and implicit language to 2D spatial arrangements, generalizes to out-of-sample data to a reasonable extent and can generate complete abstract scenes if paired with a clip-arts predictor. Finally, we qualitatively evaluate our method with a user study, validating that our generated spatial arrangements align with human expectation.</abstract>
<identifier type="citekey">radevski-etal-2020-decoding</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.408</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.408</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4549</start>
<end>4560</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decoding Language Spatial Relations to 2D Spatial Arrangements
%A Radevski, Gorjan
%A Collell, Guillem
%A Moens, Marie-Francine
%A Tuytelaars, Tinne
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F radevski-etal-2020-decoding
%X We address the problem of multimodal spatial understanding by decoding a set of language-expressed spatial relations to a set of 2D spatial arrangements in a multi-object and multi-relationship setting. We frame the task as arranging a scene of clip-arts given a textual description. We propose a simple and effective model architecture Spatial-Reasoning Bert (SR-Bert), trained to decode text to 2D spatial arrangements in a non-autoregressive manner. SR-Bert can decode both explicit and implicit language to 2D spatial arrangements, generalizes to out-of-sample data to a reasonable extent and can generate complete abstract scenes if paired with a clip-arts predictor. Finally, we qualitatively evaluate our method with a user study, validating that our generated spatial arrangements align with human expectation.
%R 10.18653/v1/2020.findings-emnlp.408
%U https://aclanthology.org/2020.findings-emnlp.408
%U https://doi.org/10.18653/v1/2020.findings-emnlp.408
%P 4549-4560
Markdown (Informal)
[Decoding Language Spatial Relations to 2D Spatial Arrangements](https://aclanthology.org/2020.findings-emnlp.408) (Radevski et al., Findings 2020)
ACL