@inproceedings{alacam-etal-2022-modeling,
title = "Modeling Referential Gaze in Task-oriented Settings of Varying Referential Complexity",
author = {Alacam, {\"O}zge and
Ruppert, Eugen and
Zarrie{\ss}, Sina and
Malhotra, Ganeshan and
Biemann, Chris and
Zarrie{\ss}, Sina},
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.19",
pages = "197--210",
abstract = "Referential gaze is a fundamental phenomenon for psycholinguistics and human-human communication. However, modeling referential gaze for real-world scenarios, e.g. for task-oriented communication, is lacking the well-deserved attention from the NLP community. In this paper, we address this challenging issue by proposing a novel multimodal NLP task; namely predicting when the gaze is referential. We further investigate how to model referential gaze and transfer gaze features to adapt to unseen situated settings that target different referential complexities than the training environment. We train (i) a sequential attention-based LSTM model and (ii) a multivariate transformer encoder architecture to predict whether the gaze is on a referent object. The models are evaluated on the three complexity datasets. The results indicate that the gaze features can be transferred not only among various similar tasks and scenes but also across various complexity levels. Taking the referential complexity of a scene into account is important for successful target prediction using gaze parameters especially when there is not much data for fine-tuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alacam-etal-2022-modeling">
<titleInfo>
<title>Modeling Referential Gaze in Task-oriented Settings of Varying Referential Complexity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Özge</namePart>
<namePart type="family">Alacam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugen</namePart>
<namePart type="family">Ruppert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganeshan</namePart>
<namePart type="family">Malhotra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<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">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</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>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Referential gaze is a fundamental phenomenon for psycholinguistics and human-human communication. However, modeling referential gaze for real-world scenarios, e.g. for task-oriented communication, is lacking the well-deserved attention from the NLP community. In this paper, we address this challenging issue by proposing a novel multimodal NLP task; namely predicting when the gaze is referential. We further investigate how to model referential gaze and transfer gaze features to adapt to unseen situated settings that target different referential complexities than the training environment. We train (i) a sequential attention-based LSTM model and (ii) a multivariate transformer encoder architecture to predict whether the gaze is on a referent object. The models are evaluated on the three complexity datasets. The results indicate that the gaze features can be transferred not only among various similar tasks and scenes but also across various complexity levels. Taking the referential complexity of a scene into account is important for successful target prediction using gaze parameters especially when there is not much data for fine-tuning.</abstract>
<identifier type="citekey">alacam-etal-2022-modeling</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.19</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>197</start>
<end>210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Referential Gaze in Task-oriented Settings of Varying Referential Complexity
%A Alacam, Özge
%A Ruppert, Eugen
%A Zarrieß, Sina
%A Malhotra, Ganeshan
%A Biemann, Chris
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F alacam-etal-2022-modeling
%X Referential gaze is a fundamental phenomenon for psycholinguistics and human-human communication. However, modeling referential gaze for real-world scenarios, e.g. for task-oriented communication, is lacking the well-deserved attention from the NLP community. In this paper, we address this challenging issue by proposing a novel multimodal NLP task; namely predicting when the gaze is referential. We further investigate how to model referential gaze and transfer gaze features to adapt to unseen situated settings that target different referential complexities than the training environment. We train (i) a sequential attention-based LSTM model and (ii) a multivariate transformer encoder architecture to predict whether the gaze is on a referent object. The models are evaluated on the three complexity datasets. The results indicate that the gaze features can be transferred not only among various similar tasks and scenes but also across various complexity levels. Taking the referential complexity of a scene into account is important for successful target prediction using gaze parameters especially when there is not much data for fine-tuning.
%U https://aclanthology.org/2022.findings-aacl.19
%P 197-210
Markdown (Informal)
[Modeling Referential Gaze in Task-oriented Settings of Varying Referential Complexity](https://aclanthology.org/2022.findings-aacl.19) (Alacam et al., Findings 2022)
ACL