@inproceedings{bhattacharyya-etal-2024-recap,
title = "{R}e{CAP}: Semantic Role Enhanced Caption Generation",
author = "Bhattacharyya, Abhidip and
Palmer, Martha and
Heckman, Christoffer",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1191",
pages = "13633--13649",
abstract = "Even though current vision language (V+L) models have achieved success in generating image captions, they often lack specificity and overlook various aspects of the image. Additionally, the attention learned through weak supervision operates opaquely and is difficult to control. To address these limitations, we propose the use of semantic roles as control signals in caption generation. Our hypothesis is that, by incorporating semantic roles as signals, the generated captions can be guided to follow specific predicate argument structures. To validate the effectiveness of our approach, we conducted experiments using data and compared the results with a baseline model VL-BART(CITATION). The experiments showed a significant improvement, with a gain of 45{\%} in Smatch score (Standard NLP evaluation metric for semantic representations), demonstrating the efficacy of our approach. By focusing on specific objects and their associated semantic roles instead of providing a general description, our framework produces captions that exhibit enhanced quality, diversity, and controllability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharyya-etal-2024-recap">
<titleInfo>
<title>ReCAP: Semantic Role Enhanced Caption Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhidip</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoffer</namePart>
<namePart type="family">Heckman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Even though current vision language (V+L) models have achieved success in generating image captions, they often lack specificity and overlook various aspects of the image. Additionally, the attention learned through weak supervision operates opaquely and is difficult to control. To address these limitations, we propose the use of semantic roles as control signals in caption generation. Our hypothesis is that, by incorporating semantic roles as signals, the generated captions can be guided to follow specific predicate argument structures. To validate the effectiveness of our approach, we conducted experiments using data and compared the results with a baseline model VL-BART(CITATION). The experiments showed a significant improvement, with a gain of 45% in Smatch score (Standard NLP evaluation metric for semantic representations), demonstrating the efficacy of our approach. By focusing on specific objects and their associated semantic roles instead of providing a general description, our framework produces captions that exhibit enhanced quality, diversity, and controllability.</abstract>
<identifier type="citekey">bhattacharyya-etal-2024-recap</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1191</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13633</start>
<end>13649</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReCAP: Semantic Role Enhanced Caption Generation
%A Bhattacharyya, Abhidip
%A Palmer, Martha
%A Heckman, Christoffer
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bhattacharyya-etal-2024-recap
%X Even though current vision language (V+L) models have achieved success in generating image captions, they often lack specificity and overlook various aspects of the image. Additionally, the attention learned through weak supervision operates opaquely and is difficult to control. To address these limitations, we propose the use of semantic roles as control signals in caption generation. Our hypothesis is that, by incorporating semantic roles as signals, the generated captions can be guided to follow specific predicate argument structures. To validate the effectiveness of our approach, we conducted experiments using data and compared the results with a baseline model VL-BART(CITATION). The experiments showed a significant improvement, with a gain of 45% in Smatch score (Standard NLP evaluation metric for semantic representations), demonstrating the efficacy of our approach. By focusing on specific objects and their associated semantic roles instead of providing a general description, our framework produces captions that exhibit enhanced quality, diversity, and controllability.
%U https://aclanthology.org/2024.lrec-main.1191
%P 13633-13649
Markdown (Informal)
[ReCAP: Semantic Role Enhanced Caption Generation](https://aclanthology.org/2024.lrec-main.1191) (Bhattacharyya et al., LREC-COLING 2024)
ACL
- Abhidip Bhattacharyya, Martha Palmer, and Christoffer Heckman. 2024. ReCAP: Semantic Role Enhanced Caption Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13633–13649, Torino, Italia. ELRA and ICCL.