@inproceedings{zhang-etal-2023-clevr,
title = "{CLEVR}-Implicit: A Diagnostic Dataset for Implicit Reasoning in Referring Expression Comprehension",
author = "Zhang, Jingwei and
Wu, Xin and
Cai, Yi",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.791/",
doi = "10.18653/v1/2023.emnlp-main.791",
pages = "12820--12830",
abstract = "Recently, pre-trained vision-language (VL) models have achieved remarkable success in various cross-modal tasks, including referring expression comprehension (REC). These models are pre-trained on the large-scale image-text pairs to learn the alignment between words in textual descriptions and objects in the corresponding images and then fine-tuned on downstream tasks. However, the performance of VL models is hindered when dealing with implicit text, which describes objects through comparisons between two or more objects rather than explicitly mentioning them. This is because the models struggle to align the implicit text with the objects in the images. To address the challenge, we introduce CLEVR-Implicit, a dataset consisting of synthetic images and corresponding two types of implicit text for the REC task. Additionally, to enhance the performance of VL models on implicit text, we propose a method called Transforming Implicit text into Explicit text (TIE), which enables VL models to reason with the implicit text. TIE consists of two modules: (1) the prompt design module builds prompts for implicit text by adding masked tokens, and (2) the cloze procedure module fine-tunes the prompts by utilizing masked language modeling (MLM) to predict the explicit words with the implicit prompts. Experimental results on our dataset demonstrate a significant improvement of 37.94{\%} in the performance of VL models on implicit text after employing our TIE method."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-clevr">
<titleInfo>
<title>CLEVR-Implicit: A Diagnostic Dataset for Implicit Reasoning in Referring Expression Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, pre-trained vision-language (VL) models have achieved remarkable success in various cross-modal tasks, including referring expression comprehension (REC). These models are pre-trained on the large-scale image-text pairs to learn the alignment between words in textual descriptions and objects in the corresponding images and then fine-tuned on downstream tasks. However, the performance of VL models is hindered when dealing with implicit text, which describes objects through comparisons between two or more objects rather than explicitly mentioning them. This is because the models struggle to align the implicit text with the objects in the images. To address the challenge, we introduce CLEVR-Implicit, a dataset consisting of synthetic images and corresponding two types of implicit text for the REC task. Additionally, to enhance the performance of VL models on implicit text, we propose a method called Transforming Implicit text into Explicit text (TIE), which enables VL models to reason with the implicit text. TIE consists of two modules: (1) the prompt design module builds prompts for implicit text by adding masked tokens, and (2) the cloze procedure module fine-tunes the prompts by utilizing masked language modeling (MLM) to predict the explicit words with the implicit prompts. Experimental results on our dataset demonstrate a significant improvement of 37.94% in the performance of VL models on implicit text after employing our TIE method.</abstract>
<identifier type="citekey">zhang-etal-2023-clevr</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.791</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.791/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12820</start>
<end>12830</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLEVR-Implicit: A Diagnostic Dataset for Implicit Reasoning in Referring Expression Comprehension
%A Zhang, Jingwei
%A Wu, Xin
%A Cai, Yi
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-clevr
%X Recently, pre-trained vision-language (VL) models have achieved remarkable success in various cross-modal tasks, including referring expression comprehension (REC). These models are pre-trained on the large-scale image-text pairs to learn the alignment between words in textual descriptions and objects in the corresponding images and then fine-tuned on downstream tasks. However, the performance of VL models is hindered when dealing with implicit text, which describes objects through comparisons between two or more objects rather than explicitly mentioning them. This is because the models struggle to align the implicit text with the objects in the images. To address the challenge, we introduce CLEVR-Implicit, a dataset consisting of synthetic images and corresponding two types of implicit text for the REC task. Additionally, to enhance the performance of VL models on implicit text, we propose a method called Transforming Implicit text into Explicit text (TIE), which enables VL models to reason with the implicit text. TIE consists of two modules: (1) the prompt design module builds prompts for implicit text by adding masked tokens, and (2) the cloze procedure module fine-tunes the prompts by utilizing masked language modeling (MLM) to predict the explicit words with the implicit prompts. Experimental results on our dataset demonstrate a significant improvement of 37.94% in the performance of VL models on implicit text after employing our TIE method.
%R 10.18653/v1/2023.emnlp-main.791
%U https://aclanthology.org/2023.emnlp-main.791/
%U https://doi.org/10.18653/v1/2023.emnlp-main.791
%P 12820-12830
Markdown (Informal)
[CLEVR-Implicit: A Diagnostic Dataset for Implicit Reasoning in Referring Expression Comprehension](https://aclanthology.org/2023.emnlp-main.791/) (Zhang et al., EMNLP 2023)
ACL