Compositionality is a core property of natural language, and compositional behavior (CB) is a crucial goal for modern NLP systems. The research literature, however, includes conflicting perspectives on how CB should be defined, evaluated, and achieved. We propose a conceptual framework to address these questions and survey researchers active in this area.We find consensus on several key points. Researchers broadly accept our proposed definition of CB, agree that it is not solved by current models, and doubt that scale alone will achieve the target behavior. In other areas, we find the field is split on how to move forward, identifying diverse opportunities for future research.
Kate McCurdy, Paul Soulos, Paul Smolensky, Roland Fernandez, and Jianfeng Gao. 2024.Toward Compositional Behavior in Neural Models: A Survey of Current Views. InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9323–9339, Miami, Florida, USA. Association for Computational Linguistics.
@inproceedings{mccurdy-etal-2024-toward, title = "Toward Compositional Behavior in Neural Models: A Survey of Current Views", author = "McCurdy, Kate and Soulos, Paul and Smolensky, Paul and Fernandez, Roland and Gao, Jianfeng", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.emnlp-main.524/", doi = "10.18653/v1/2024.emnlp-main.524", pages = "9323--9339", abstract = "Compositionality is a core property of natural language, and compositional behavior (CB) is a crucial goal for modern NLP systems. The research literature, however, includes conflicting perspectives on how CB should be defined, evaluated, and achieved. We propose a conceptual framework to address these questions and survey researchers active in this area.We find consensus on several key points. Researchers broadly accept our proposed definition of CB, agree that it is not solved by current models, and doubt that scale alone will achieve the target behavior. In other areas, we find the field is split on how to move forward, identifying diverse opportunities for future research."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="mccurdy-etal-2024-toward"> <titleInfo> <title>Toward Compositional Behavior in Neural Models: A Survey of Current Views</title> </titleInfo> <name type="personal"> <namePart type="given">Kate</namePart> <namePart type="family">McCurdy</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Paul</namePart> <namePart type="family">Soulos</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Paul</namePart> <namePart type="family">Smolensky</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Roland</namePart> <namePart type="family">Fernandez</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Jianfeng</namePart> <namePart type="family">Gao</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2024-11</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title> </titleInfo> <name type="personal"> <namePart type="given">Yaser</namePart> <namePart type="family">Al-Onaizan</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Mohit</namePart> <namePart type="family">Bansal</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Yun-Nung</namePart> <namePart type="family">Chen</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Miami, Florida, USA</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Compositionality is a core property of natural language, and compositional behavior (CB) is a crucial goal for modern NLP systems. The research literature, however, includes conflicting perspectives on how CB should be defined, evaluated, and achieved. We propose a conceptual framework to address these questions and survey researchers active in this area.We find consensus on several key points. Researchers broadly accept our proposed definition of CB, agree that it is not solved by current models, and doubt that scale alone will achieve the target behavior. In other areas, we find the field is split on how to move forward, identifying diverse opportunities for future research.</abstract> <identifier type="citekey">mccurdy-etal-2024-toward</identifier> <identifier type="doi">10.18653/v1/2024.emnlp-main.524</identifier> <location> <url>https://aclanthology.org/2024.emnlp-main.524/</url> </location> <part> <date>2024-11</date> <extent unit="page"> <start>9323</start> <end>9339</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Toward Compositional Behavior in Neural Models: A Survey of Current Views%A McCurdy, Kate%A Soulos, Paul%A Smolensky, Paul%A Fernandez, Roland%A Gao, Jianfeng%Y Al-Onaizan, Yaser%Y Bansal, Mohit%Y Chen, Yun-Nung%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing%D 2024%8 November%I Association for Computational Linguistics%C Miami, Florida, USA%F mccurdy-etal-2024-toward%X Compositionality is a core property of natural language, and compositional behavior (CB) is a crucial goal for modern NLP systems. The research literature, however, includes conflicting perspectives on how CB should be defined, evaluated, and achieved. We propose a conceptual framework to address these questions and survey researchers active in this area.We find consensus on several key points. Researchers broadly accept our proposed definition of CB, agree that it is not solved by current models, and doubt that scale alone will achieve the target behavior. In other areas, we find the field is split on how to move forward, identifying diverse opportunities for future research.%R 10.18653/v1/2024.emnlp-main.524%U https://aclanthology.org/2024.emnlp-main.524/%U https://doi.org/10.18653/v1/2024.emnlp-main.524%P 9323-9339
[Toward Compositional Behavior in Neural Models: A Survey of Current Views](https://aclanthology.org/2024.emnlp-main.524/) (McCurdy et al., EMNLP 2024)
Kate McCurdy, Paul Soulos, Paul Smolensky, Roland Fernandez, and Jianfeng Gao. 2024.Toward Compositional Behavior in Neural Models: A Survey of Current Views. InProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9323–9339, Miami, Florida, USA. Association for Computational Linguistics.