@inproceedings{akula-etal-2022-alfred,
title = "{ALFRED}-{L}: Investigating the Role of Language for Action Learning in Interactive Visual Environments",
author = "Akula, Arjun and
Gella, Spandana and
Padmakumar, Aishwarya and
Namazifar, Mahdi and
Bansal, Mohit and
Thomason, Jesse and
Hakkani-Tur, Dilek",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.636",
doi = "10.18653/v1/2022.emnlp-main.636",
pages = "9369--9378",
abstract = "Embodied Vision and Language Task Completion requires an embodied agent to interpret natural language instructions and egocentric visual observations to navigate through and interact with environments. In this work, we examine ALFRED, a challenging benchmark for embodied task completion, with the goal of gaining insight into how effectively models utilize language. We find evidence that sequence-to-sequence and transformer-based models trained on this benchmark are not sufficiently sensitive to changes in input language instructions. Next, we construct a new test split {--} ALFRED-L to test whether ALFRED models can generalize to task structures not seen during training that intuitively require the same types of language understanding required in ALFRED. Evaluation of existing models on ALFRED-L suggests that (a) models are overly reliant on the sequence in which objects are visited in typical ALFRED trajectories and fail to adapt to modifications of this sequence and (b) models trained with additional augmented trajectories are able to adapt relatively better to such changes in input language instructions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akula-etal-2022-alfred">
<titleInfo>
<title>ALFRED-L: Investigating the Role of Language for Action Learning in Interactive Visual Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahdi</namePart>
<namePart type="family">Namazifar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Thomason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Embodied Vision and Language Task Completion requires an embodied agent to interpret natural language instructions and egocentric visual observations to navigate through and interact with environments. In this work, we examine ALFRED, a challenging benchmark for embodied task completion, with the goal of gaining insight into how effectively models utilize language. We find evidence that sequence-to-sequence and transformer-based models trained on this benchmark are not sufficiently sensitive to changes in input language instructions. Next, we construct a new test split – ALFRED-L to test whether ALFRED models can generalize to task structures not seen during training that intuitively require the same types of language understanding required in ALFRED. Evaluation of existing models on ALFRED-L suggests that (a) models are overly reliant on the sequence in which objects are visited in typical ALFRED trajectories and fail to adapt to modifications of this sequence and (b) models trained with additional augmented trajectories are able to adapt relatively better to such changes in input language instructions.</abstract>
<identifier type="citekey">akula-etal-2022-alfred</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.636</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.636</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>9369</start>
<end>9378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ALFRED-L: Investigating the Role of Language for Action Learning in Interactive Visual Environments
%A Akula, Arjun
%A Gella, Spandana
%A Padmakumar, Aishwarya
%A Namazifar, Mahdi
%A Bansal, Mohit
%A Thomason, Jesse
%A Hakkani-Tur, Dilek
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F akula-etal-2022-alfred
%X Embodied Vision and Language Task Completion requires an embodied agent to interpret natural language instructions and egocentric visual observations to navigate through and interact with environments. In this work, we examine ALFRED, a challenging benchmark for embodied task completion, with the goal of gaining insight into how effectively models utilize language. We find evidence that sequence-to-sequence and transformer-based models trained on this benchmark are not sufficiently sensitive to changes in input language instructions. Next, we construct a new test split – ALFRED-L to test whether ALFRED models can generalize to task structures not seen during training that intuitively require the same types of language understanding required in ALFRED. Evaluation of existing models on ALFRED-L suggests that (a) models are overly reliant on the sequence in which objects are visited in typical ALFRED trajectories and fail to adapt to modifications of this sequence and (b) models trained with additional augmented trajectories are able to adapt relatively better to such changes in input language instructions.
%R 10.18653/v1/2022.emnlp-main.636
%U https://aclanthology.org/2022.emnlp-main.636
%U https://doi.org/10.18653/v1/2022.emnlp-main.636
%P 9369-9378
Markdown (Informal)
[ALFRED-L: Investigating the Role of Language for Action Learning in Interactive Visual Environments](https://aclanthology.org/2022.emnlp-main.636) (Akula et al., EMNLP 2022)
ACL