@inproceedings{xu-etal-2024-exploiting,
title = "Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization",
author = "Xu, Zhe and
Wei, Kun and
Yang, Xu and
Deng, Cheng",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.247",
doi = "10.18653/v1/2024.acl-long.247",
pages = "4511--4521",
abstract = "Weakly supervised natural language video localization (WS-NLVL) aims to retrieve the moment corresponding to a language query in a video with only video-language pairs utilized during training. Despite great success, existing WS-NLVL methods seldomly consider the complex temporal relations enclosing the language query (e.g., between the language query and sub-queries decomposed from it or its synonymous query), yielding illogical predictions. In this paper, we propose a novel plug-and-play method, Intrinsic Multilateral Logical Rules, namely IMLR, to exploit intrinsic temporal relations and logical rules for WS-NLVL. Specifically, we formalize queries derived from the original language query as the nodes of a directed graph, i.e., intrinsic temporal relation graph (ITRG), and the temporal relations between them as the edges. Instead of directly prompting a pre-trained language model, a relation-guided prompting method is introduced to generate ITRG in a hierarchical manner. We customize four types of multilateral temporal logical rules (i.e., identity, inclusion, synchronization, and succession) from ITRG and utilize them to train our model. Experiments demonstrate the effectiveness and superiority of our method on the Charades-STA and ActivityNet Captions datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-exploiting">
<titleInfo>
<title>Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Weakly supervised natural language video localization (WS-NLVL) aims to retrieve the moment corresponding to a language query in a video with only video-language pairs utilized during training. Despite great success, existing WS-NLVL methods seldomly consider the complex temporal relations enclosing the language query (e.g., between the language query and sub-queries decomposed from it or its synonymous query), yielding illogical predictions. In this paper, we propose a novel plug-and-play method, Intrinsic Multilateral Logical Rules, namely IMLR, to exploit intrinsic temporal relations and logical rules for WS-NLVL. Specifically, we formalize queries derived from the original language query as the nodes of a directed graph, i.e., intrinsic temporal relation graph (ITRG), and the temporal relations between them as the edges. Instead of directly prompting a pre-trained language model, a relation-guided prompting method is introduced to generate ITRG in a hierarchical manner. We customize four types of multilateral temporal logical rules (i.e., identity, inclusion, synchronization, and succession) from ITRG and utilize them to train our model. Experiments demonstrate the effectiveness and superiority of our method on the Charades-STA and ActivityNet Captions datasets.</abstract>
<identifier type="citekey">xu-etal-2024-exploiting</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.247</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.247</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4511</start>
<end>4521</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization
%A Xu, Zhe
%A Wei, Kun
%A Yang, Xu
%A Deng, Cheng
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F xu-etal-2024-exploiting
%X Weakly supervised natural language video localization (WS-NLVL) aims to retrieve the moment corresponding to a language query in a video with only video-language pairs utilized during training. Despite great success, existing WS-NLVL methods seldomly consider the complex temporal relations enclosing the language query (e.g., between the language query and sub-queries decomposed from it or its synonymous query), yielding illogical predictions. In this paper, we propose a novel plug-and-play method, Intrinsic Multilateral Logical Rules, namely IMLR, to exploit intrinsic temporal relations and logical rules for WS-NLVL. Specifically, we formalize queries derived from the original language query as the nodes of a directed graph, i.e., intrinsic temporal relation graph (ITRG), and the temporal relations between them as the edges. Instead of directly prompting a pre-trained language model, a relation-guided prompting method is introduced to generate ITRG in a hierarchical manner. We customize four types of multilateral temporal logical rules (i.e., identity, inclusion, synchronization, and succession) from ITRG and utilize them to train our model. Experiments demonstrate the effectiveness and superiority of our method on the Charades-STA and ActivityNet Captions datasets.
%R 10.18653/v1/2024.acl-long.247
%U https://aclanthology.org/2024.acl-long.247
%U https://doi.org/10.18653/v1/2024.acl-long.247
%P 4511-4521
Markdown (Informal)
[Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization](https://aclanthology.org/2024.acl-long.247) (Xu et al., ACL 2024)
ACL