@inproceedings{rajaby-faghihi-etal-2020-latent,
title = "Latent Alignment of Procedural Concepts in Multimodal Recipes",
author = "Rajaby Faghihi, Hossein and
Mirzaee, Roshanak and
Paliwal, Sudarshan and
Kordjamshidi, Parisa",
editor = "Wang, Xin and
Thomason, Jesse and
Hu, Ronghang and
Chen, Xinlei and
Anderson, Peter and
Wu, Qi and
Celikyilmaz, Asli and
Baldridge, Jason and
Wang, William Yang",
booktitle = "Proceedings of the First Workshop on Advances in Language and Vision Research",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.alvr-1.5/",
doi = "10.18653/v1/2020.alvr-1.5",
pages = "26--31",
abstract = "We propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. Our model is solving the textual cloze task which is a reading comprehension on a recipe containing images and instructions. We exploit the power of attention networks, cross-modal representations, and a latent alignment space between instructions and candidate answers to solve the problem. We introduce constrained max-pooling which refines the max pooling operation on the alignment matrix to impose disjoint constraints among the outputs of the model. Our evaluation result indicates a 19{\%} improvement over the baselines."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajaby-faghihi-etal-2020-latent">
<titleInfo>
<title>Latent Alignment of Procedural Concepts in Multimodal Recipes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Rajaby Faghihi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roshanak</namePart>
<namePart type="family">Mirzaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudarshan</namePart>
<namePart type="family">Paliwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Advances in Language and Vision Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Thomason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronghang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinlei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</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">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</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 propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. Our model is solving the textual cloze task which is a reading comprehension on a recipe containing images and instructions. We exploit the power of attention networks, cross-modal representations, and a latent alignment space between instructions and candidate answers to solve the problem. We introduce constrained max-pooling which refines the max pooling operation on the alignment matrix to impose disjoint constraints among the outputs of the model. Our evaluation result indicates a 19% improvement over the baselines.</abstract>
<identifier type="citekey">rajaby-faghihi-etal-2020-latent</identifier>
<identifier type="doi">10.18653/v1/2020.alvr-1.5</identifier>
<location>
<url>https://aclanthology.org/2020.alvr-1.5/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>26</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latent Alignment of Procedural Concepts in Multimodal Recipes
%A Rajaby Faghihi, Hossein
%A Mirzaee, Roshanak
%A Paliwal, Sudarshan
%A Kordjamshidi, Parisa
%Y Wang, Xin
%Y Thomason, Jesse
%Y Hu, Ronghang
%Y Chen, Xinlei
%Y Anderson, Peter
%Y Wu, Qi
%Y Celikyilmaz, Asli
%Y Baldridge, Jason
%Y Wang, William Yang
%S Proceedings of the First Workshop on Advances in Language and Vision Research
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F rajaby-faghihi-etal-2020-latent
%X We propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. Our model is solving the textual cloze task which is a reading comprehension on a recipe containing images and instructions. We exploit the power of attention networks, cross-modal representations, and a latent alignment space between instructions and candidate answers to solve the problem. We introduce constrained max-pooling which refines the max pooling operation on the alignment matrix to impose disjoint constraints among the outputs of the model. Our evaluation result indicates a 19% improvement over the baselines.
%R 10.18653/v1/2020.alvr-1.5
%U https://aclanthology.org/2020.alvr-1.5/
%U https://doi.org/10.18653/v1/2020.alvr-1.5
%P 26-31
Markdown (Informal)
[Latent Alignment of Procedural Concepts in Multimodal Recipes](https://aclanthology.org/2020.alvr-1.5/) (Rajaby Faghihi et al., ALVR 2020)
ACL