@inproceedings{alacam-2021-situation,
title = "Situation-Specific Multimodal Feature Adaptation",
author = {Alacam, {\"O}zge},
editor = "Blodgett, Su Lin and
Madaio, Michael and
O'Connor, Brendan and
Wallach, Hanna and
Yang, Qian",
booktitle = "Proceedings of the First Workshop on Bridging Human{--}Computer Interaction and Natural Language Processing",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.hcinlp-1.13",
pages = "81--87",
abstract = "In the next decade, we will see a considerable need for NLP models for situated settings where diversity of situations and also different modalities including eye-movements should be taken into account in order to grasp the intention of the user. However, language comprehension in situated settings can not be handled in isolation, where different multimodal cues are inherently present and essential parts of the situations. In this research proposal, we aim to quantify the influence of each modality in interaction with various referential complexities. We propose to encode the referential complexity of the situated settings in the embeddings during pre-training to implicitly guide the model to the most plausible situation-specific deviations. We summarize the challenges of intention extraction and propose a methodological approach to investigate a situation-specific feature adaptation to improve crossmodal mapping and meaning recovery from noisy communication settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alacam-2021-situation">
<titleInfo>
<title>Situation-Specific Multimodal Feature Adaptation</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>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Madaio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brendan</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Wallach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Yang</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>In the next decade, we will see a considerable need for NLP models for situated settings where diversity of situations and also different modalities including eye-movements should be taken into account in order to grasp the intention of the user. However, language comprehension in situated settings can not be handled in isolation, where different multimodal cues are inherently present and essential parts of the situations. In this research proposal, we aim to quantify the influence of each modality in interaction with various referential complexities. We propose to encode the referential complexity of the situated settings in the embeddings during pre-training to implicitly guide the model to the most plausible situation-specific deviations. We summarize the challenges of intention extraction and propose a methodological approach to investigate a situation-specific feature adaptation to improve crossmodal mapping and meaning recovery from noisy communication settings.</abstract>
<identifier type="citekey">alacam-2021-situation</identifier>
<location>
<url>https://aclanthology.org/2021.hcinlp-1.13</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>81</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Situation-Specific Multimodal Feature Adaptation
%A Alacam, Özge
%Y Blodgett, Su Lin
%Y Madaio, Michael
%Y O’Connor, Brendan
%Y Wallach, Hanna
%Y Yang, Qian
%S Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F alacam-2021-situation
%X In the next decade, we will see a considerable need for NLP models for situated settings where diversity of situations and also different modalities including eye-movements should be taken into account in order to grasp the intention of the user. However, language comprehension in situated settings can not be handled in isolation, where different multimodal cues are inherently present and essential parts of the situations. In this research proposal, we aim to quantify the influence of each modality in interaction with various referential complexities. We propose to encode the referential complexity of the situated settings in the embeddings during pre-training to implicitly guide the model to the most plausible situation-specific deviations. We summarize the challenges of intention extraction and propose a methodological approach to investigate a situation-specific feature adaptation to improve crossmodal mapping and meaning recovery from noisy communication settings.
%U https://aclanthology.org/2021.hcinlp-1.13
%P 81-87
Markdown (Informal)
[Situation-Specific Multimodal Feature Adaptation](https://aclanthology.org/2021.hcinlp-1.13) (Alacam, HCINLP 2021)
ACL
- Özge Alacam. 2021. Situation-Specific Multimodal Feature Adaptation. In Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing, pages 81–87, Online. Association for Computational Linguistics.