A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL, with a 7.6% absolute increase in Avg. JGA and an 11% absolute rise in BWT metrics over existing state-of-the-art methods. The source code is provided for reproducibility.
Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan Shi, Bo Liu, and Xiao-Ming Wu. 2024.TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1266–1279, Bangkok, Thailand. Association for Computational Linguistics.
@inproceedings{feng-etal-2024-tasl, title = "{T}a{SL}: Continual Dialog State Tracking via Task Skill Localization and Consolidation", author = "Feng, Yujie and Chu, Xu and Xu, Yongxin and Shi, Guangyuan and Liu, Bo and Wu, Xiao-Ming", 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.69/", doi = "10.18653/v1/2024.acl-long.69", pages = "1266--1279", abstract = "A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL, with a 7.6{\%} absolute increase in Avg. JGA and an 11{\%} absolute rise in BWT metrics over existing state-of-the-art methods. The source code is provided for reproducibility."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="feng-etal-2024-tasl"> <titleInfo> <title>TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation</title> </titleInfo> <name type="personal"> <namePart type="given">Yujie</namePart> <namePart type="family">Feng</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Xu</namePart> <namePart type="family">Chu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Yongxin</namePart> <namePart type="family">Xu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Guangyuan</namePart> <namePart type="family">Shi</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Bo</namePart> <namePart type="family">Liu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Xiao-Ming</namePart> <namePart type="family">Wu</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>A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL, with a 7.6% absolute increase in Avg. JGA and an 11% absolute rise in BWT metrics over existing state-of-the-art methods. The source code is provided for reproducibility.</abstract> <identifier type="citekey">feng-etal-2024-tasl</identifier> <identifier type="doi">10.18653/v1/2024.acl-long.69</identifier> <location> <url>https://aclanthology.org/2024.acl-long.69/</url> </location> <part> <date>2024-08</date> <extent unit="page"> <start>1266</start> <end>1279</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation%A Feng, Yujie%A Chu, Xu%A Xu, Yongxin%A Shi, Guangyuan%A Liu, Bo%A Wu, Xiao-Ming%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 feng-etal-2024-tasl%X A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL, with a 7.6% absolute increase in Avg. JGA and an 11% absolute rise in BWT metrics over existing state-of-the-art methods. The source code is provided for reproducibility.%R 10.18653/v1/2024.acl-long.69%U https://aclanthology.org/2024.acl-long.69/%U https://doi.org/10.18653/v1/2024.acl-long.69%P 1266-1279
[TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation](https://aclanthology.org/2024.acl-long.69/) (Feng et al., ACL 2024)
Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan Shi, Bo Liu, and Xiao-Ming Wu. 2024.TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1266–1279, Bangkok, Thailand. Association for Computational Linguistics.