{"title":"Compositionality in Computational Linguistics","authors":"L. Donatelli, Alexander Koller","doi":"10.1146/annurev-linguistics-030521-044439","DOIUrl":null,"url":null,"abstract":"Neural models greatly outperform grammar-based models across many tasks in modern computational linguistics. This raises the question of whether linguistic principles, such as the Principle of Compositionality, still have value as modeling tools. We review the recent literature and find that while an overly strict interpretation of compositionality makes it hard to achieve broad coverage in semantic parsing tasks, compositionality is still necessary for a model to learn the correct linguistic generalizations from limited data. Reconciling both of these qualities requires the careful exploration of a novel design space; we also review some recent results that may help in this exploration. Expected final online publication date for the Annual Review of Linguistics, Volume 9 is January 2023. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.","PeriodicalId":45803,"journal":{"name":"Annual Review of Linguistics","volume":"45 1","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annual Review of Linguistics","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1146/annurev-linguistics-030521-044439","RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"LANGUAGE & LINGUISTICS","Score":null,"Total":0}
引用次数: 2
Abstract
Neural models greatly outperform grammar-based models across many tasks in modern computational linguistics. This raises the question of whether linguistic principles, such as the Principle of Compositionality, still have value as modeling tools. We review the recent literature and find that while an overly strict interpretation of compositionality makes it hard to achieve broad coverage in semantic parsing tasks, compositionality is still necessary for a model to learn the correct linguistic generalizations from limited data. Reconciling both of these qualities requires the careful exploration of a novel design space; we also review some recent results that may help in this exploration. Expected final online publication date for the Annual Review of Linguistics, Volume 9 is January 2023. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.
期刊介绍:
The Annual Review of Linguistics, in publication since 2015, covers significant developments in the field of linguistics, including phonetics, phonology, morphology, syntax, semantics, pragmatics, and their interfaces. Reviews synthesize advances in linguistic theory, sociolinguistics, psycholinguistics, neurolinguistics, language change, biology and evolution of language, typology, as well as applications of linguistics in many domains.