{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T05:21:25Z","timestamp":1771478485951,"version":"3.50.1"},"reference-count":170,"publisher":"MIT Press","issue":"1","license":[{"start":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T00:00:00Z","timestamp":1726704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>One of the major outstanding questions in computational semantics is how humans integrate the meaning of individual words into a sentence in a way that enables understanding of complex and novel combinations of words, a phenomenon known as compositionality. Many approaches to modeling the process of compositionality can be classified as either \u201cvector-based\u201d models, in which the meaning of a sentence is represented as a vector of numbers, or \u201csyntax-based\u201d models, in which the meaning of a sentence is represented as a structured tree of labeled components. A major barrier in assessing and comparing these contrasting approaches is the lack of large, relevant datasets for model comparison. This article aims to address this gap by introducing a new dataset, STS3k, which consists of 2,800 pairs of sentences rated for semantic similarity by human participants. The sentence pairs have been selected to systematically vary different combinations of words, providing a rigorous test and enabling a clearer picture of the comparative strengths and weaknesses of vector-based and syntax-based methods. Our results show that when tested on the new STS3k dataset, state-of-the-art transformers poorly capture the pattern of human semantic similarity judgments, while even simple methods for combining syntax- and vector-based components into a novel hybrid model yield substantial improvements. We further show that this improvement is due to the ability of the hybrid model to replicate human sensitivity to specific changes in sentence structure. Our findings provide evidence for the value of integrating multiple methods to better reflect the way in which humans mentally represent compositional meaning.<\/jats:p>","DOI":"10.1162\/coli_a_00536","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T15:59:17Z","timestamp":1726761557000},"page":"139-190","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":8,"title":["Compositionality and Sentence Meaning: Comparing Semantic Parsing and Transformers on a Challenging Sentence Similarity Dataset"],"prefix":"10.1162","volume":"51","author":[{"given":"James","family":"Fodor","sequence":"first","affiliation":[{"name":"The University of Melbourne, The Centre for Brain, Mind and Markets. fods12@gmail.com"}]},{"given":"Simon De","family":"Deyne","sequence":"additional","affiliation":[{"name":"The University of Melbourne, School of Psychological Sciences. simon.dedeyne@unimelb.edu.au"}]},{"given":"Shinsuke","family":"Suzuki","sequence":"additional","affiliation":[{"name":"Hitotsubashi University, Faculty of Social Data Science. shinsuke.szk@gmail.com"}]}],"member":"281","published-online":{"date-parts":[[2025,3,15]]},"reference":[{"key":"2025032113503891300_bib1","doi-asserted-by":"publisher","first-page":"782","DOI":"10.18653\/v1\/2023.eacl-main.55","article-title":"What makes sentences semantically related? A textual relatedness dataset and empirical study","volume-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics","author":"Abdalla","year":"2023"},{"key":"2025032113503891300_bib2","doi-asserted-by":"crossref","first-page":"70","DOI":"10.18653\/v1\/2022.eval4nlp-1.8","article-title":"Why is sentence similarity benchmark not predictive of application-oriented task performance?","volume-title":"Proceedings of the 3rd Workshop on Evaluation and Comparison of NLP Systems","author":"Abe","year":"2022"},{"key":"2025032113503891300_bib3","first-page":"228","article-title":"Universal conceptual cognitive annotation (UCCA)","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Abend","year":"2013"},{"key":"2025032113503891300_bib4","doi-asserted-by":"publisher","first-page":"497","DOI":"10.18653\/v1\/S16-1081","article-title":"SemEval-2016 Task 1: Semantic textual similarity, monolingual and cross-lingual evaluation","volume-title":"SemEval-2016. 10th International Workshop on Semantic Evaluation","author":"Agirre","year":"2016"},{"issue":"1","key":"2025032113503891300_bib5","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1080\/01690960902840279","article-title":"A computational model of learning semantic roles from child-directed language","volume":"25","author":"Alishahi","year":"2010","journal-title":"Language and Cognitive Processes"},{"key":"2025032113503891300_bib6","article-title":"Word embeddings: A survey","author":"Almeida","year":"2019","journal-title":"arXiv preprint arXiv:1901.09069"},{"issue":"4","key":"2025032113503891300_bib7","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1162\/coli_a_00454","article-title":"Information theory\u2013based compositional distributional semantics","volume":"48","author":"Amig\u00f3","year":"2022","journal-title":"Computational Linguistics"},{"key":"2025032113503891300_bib8","doi-asserted-by":"publisher","first-page":"505","DOI":"10.18653\/v1\/N19-1050","article-title":"Big BiRD: A large, fine-grained, bigram relatedness dataset for examining semantic composition","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Asaadi","year":"2019"},{"key":"2025032113503891300_bib9","doi-asserted-by":"publisher","first-page":"103649","DOI":"10.1016\/j.artint.2021.103649","article-title":"Logic tensor networks","volume":"303","author":"Badreddine","year":"2022","journal-title":"Artificial Intelligence"},{"key":"2025032113503891300_bib10","doi-asserted-by":"publisher","first-page":"3011","DOI":"10.18653\/v1\/2021.eacl-main.262","article-title":"Syntax-BERT: Improving pre-trained transformers with syntax trees","volume-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","author":"Bai","year":"2021"},{"key":"2025032113503891300_bib11","doi-asserted-by":"publisher","first-page":"6001","DOI":"10.18653\/v1\/2022.acl-long.415","article-title":"Graph pre-training for AMR parsing and generation","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Bai","year":"2022"},{"key":"2025032113503891300_bib12","article-title":"A survey of word embeddings evaluation methods","author":"Bakarov","year":"2018","journal-title":"arXiv preprint arXiv:1801.09536"},{"key":"2025032113503891300_bib13","doi-asserted-by":"publisher","first-page":"86","DOI":"10.3115\/980451.980860","article-title":"The Berkeley FrameNet project","volume-title":"COLING 1998 Volume 1: The 17th International Conference on Computational Linguistics","author":"Baker","year":"1998"},{"key":"2025032113503891300_bib14","first-page":"1402","article-title":"Deep-syntactic parsing","volume-title":"Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers","author":"Ballesteros","year":"2014"},{"key":"2025032113503891300_bib15","first-page":"178","article-title":"Abstract meaning representation for sembanking","volume-title":"Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse","author":"Banarescu","year":"2013"},{"issue":"1791","key":"2025032113503891300_bib16","doi-asserted-by":"publisher","first-page":"20190307","DOI":"10.1098\/rstb.2019.0307","article-title":"Linguistic generalization and compositionality in modern artificial neural networks","volume":"375","author":"Baroni","year":"2020","journal-title":"Philosophical Transactions of the Royal Society B"},{"key":"2025032113503891300_bib17","doi-asserted-by":"publisher","first-page":"241","DOI":"10.33011\/lilt.v9i.1321","article-title":"Frege in space: A program for compositional distributional semantics","volume":"9","author":"Baroni","year":"2014","journal-title":"Linguistic Issues in Language Technology"},{"key":"2025032113503891300_bib18","doi-asserted-by":"publisher","first-page":"7","DOI":"10.18653\/v1\/W16-2502","article-title":"A critique of word similarity as a method for evaluating distributional semantic models","volume-title":"Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP","author":"Batchkarov","year":"2016"},{"issue":"4","key":"2025032113503891300_bib19","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1162\/COLI_a_00266","article-title":"Representing meaning with a combination of logical and distributional models","volume":"42","author":"Beltagy","year":"2016","journal-title":"Computational Linguistics"},{"key":"2025032113503891300_bib20","first-page":"21","article-title":"Sentence paraphrase detection: When determiners and word order make the difference","volume-title":"Proceedings of the IWCS 2013 Workshop Towards a Formal Distributional Semantics","author":"Bernardi","year":"2013"},{"key":"2025032113503891300_bib21","doi-asserted-by":"publisher","first-page":"12564","DOI":"10.1609\/aaai.v35i14.17489","article-title":"One SPRING to rule them both: Symmetric AMR semantic parsing and generation without a complex pipeline","volume-title":"Proceedings of AAAI","author":"Bevilacqua","year":"2021"},{"key":"2025032113503891300_bib22","first-page":"546","article-title":"A comparison of vector-based representations for semantic composition","volume-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning","author":"Blacoe","year":"2012"},{"issue":"5","key":"2025032113503891300_bib23","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1111\/cogs.12265","article-title":"Concepts as semantic pointers: A framework and computational model","volume":"40","author":"Blouw","year":"2016","journal-title":"Cognitive Science"},{"key":"2025032113503891300_bib24","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1146\/annurev-linguistics-011619-030303","article-title":"Distributional semantics and linguistic theory","volume":"6","author":"Boleda","year":"2020","journal-title":"Annual Review of Linguistics"},{"issue":"4","key":"2025032113503891300_bib25","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1162\/COLI_a_00261","article-title":"Formal distributional semantics: Introduction to the special issue","volume":"42","author":"Boleda","year":"2016","journal-title":"Computational Linguistics"},{"key":"2025032113503891300_bib26","doi-asserted-by":"publisher","first-page":"119103","DOI":"10.1016\/j.eswa.2022.119103","article-title":"A siamese neural network for learning semantically-informed sentence embeddings","volume":"214","author":"B\u00f6l\u00fcc\u00fc","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"2025032113503891300_bib27","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"key":"2025032113503891300_bib28","first-page":"748","article-title":"Smatch: An evaluation metric for semantic feature structures","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Cai","year":"2013"},{"key":"2025032113503891300_bib29","article-title":"Isotropy in the contextual embedding space: Clusters and manifolds","volume-title":"International Conference on Learning Representations","author":"Cai","year":"2021"},{"key":"2025032113503891300_bib30","doi-asserted-by":"publisher","first-page":"169","DOI":"10.18653\/v1\/D18-2029","article-title":"Universal sentence encoder for English","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Cer","year":"2018"},{"key":"2025032113503891300_bib31","doi-asserted-by":"publisher","first-page":"166395","DOI":"10.1109\/ACCESS.2021.3135807","article-title":"Comparative analysis of word embeddings in assessing semantic similarity of complex sentences","volume":"9","author":"Chandrasekaran","year":"2021","journal-title":"IEEE Access"},{"issue":"3","key":"2025032113503891300_bib32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","article-title":"A survey on evaluation of large language models","volume":"15","author":"Chang","year":"2023","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"issue":"4","key":"2025032113503891300_bib33","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1017\/S1351324919000214","article-title":"A structured distributional model of sentence meaning and processing","volume":"25","author":"Chersoni","year":"2019","journal-title":"Natural Language Engineering"},{"issue":"3","key":"2025032113503891300_bib34","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TIT.1956.1056813","article-title":"Three models for the description of language","volume":"2","author":"Chomsky","year":"1956","journal-title":"IRE Transactions on Information Theory"},{"key":"2025032113503891300_bib35","doi-asserted-by":"publisher","first-page":"276","DOI":"10.18653\/v1\/W19-4828","article-title":"What does BERT look at? An analysis of BERT\u2019s attention","volume-title":"Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","author":"Clark","year":"2019"},{"key":"2025032113503891300_bib36","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1002\/9781118882139.ch16","article-title":"Vector space models of lexical meaning","author":"Clark","year":"2015","journal-title":"The Handbook of Contemporary Semantic Theory"},{"key":"2025032113503891300_bib37","article-title":"Combining pre-trained language models and structured knowledge","author":"Colon-Hernandez","year":"2021","journal-title":"arXiv preprint arXiv:2101.12294"},{"key":"2025032113503891300_bib38","doi-asserted-by":"publisher","first-page":"670","DOI":"10.18653\/v1\/D17-1070","article-title":"Supervised learning of universal sentence representations from natural language inference data","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Conneau","year":"2017"},{"issue":"1","key":"2025032113503891300_bib39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/coli_a_00341","article-title":"Unsupervised compositionality prediction of nominal compounds","volume":"45","author":"Cordeiro","year":"2019","journal-title":"Computational Linguistics"},{"key":"2025032113503891300_bib40","doi-asserted-by":"publisher","first-page":"619","DOI":"10.18653\/v1\/2021.emnlp-main.49","article-title":"The devil is in the detail: Simple tricks improve systematic generalization of transformers","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Csord\u00e1s","year":"2021"},{"key":"2025032113503891300_bib41","doi-asserted-by":"publisher","first-page":"4154","DOI":"10.18653\/v1\/2022.acl-long.286","article-title":"The paradox of the compositionality of natural language: A neural machine translation case study","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Dankers","year":"2022"},{"issue":"6","key":"2025032113503891300_bib42","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6&lt;391::AID-ASI1&gt;3.0.CO;2-9","article-title":"Indexing by latent semantic analysis","volume":"41","author":"Deerwester","year":"1990","journal-title":"Journal of the American Society for Information Science"},{"key":"2025032113503891300_bib43","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2019","journal-title":"ArXiv"},{"key":"2025032113503891300_bib44","first-page":"9","article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Third International Workshop on Paraphrasing (IWP2005)","author":"Dolan","year":"2005"},{"key":"2025032113503891300_bib45","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-linguistics-030521-044439","article-title":"Compositionality in computational linguistics","volume":"9","author":"Donatelli","year":"2023","journal-title":"Annual Review of Linguistics"},{"issue":"3","key":"2025032113503891300_bib46","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1162\/coli_a_00445","article-title":"Position information in transformers: An overview","volume":"48","author":"Dufter","year":"2022","journal-title":"Computational Linguistics"},{"key":"2025032113503891300_bib47","article-title":"Faith and fate: Limits of transformers on compositionality","author":"Dziri","year":"2023","journal-title":"arXiv preprint arXiv:2305.18654"},{"key":"2025032113503891300_bib48","doi-asserted-by":"publisher","first-page":"55","DOI":"10.18653\/v1\/W19-4308","article-title":"Pitfalls in the evaluation of sentence embeddings","volume-title":"Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","author":"Eger","year":"2019"},{"key":"2025032113503891300_bib49","doi-asserted-by":"publisher","first-page":"7436","DOI":"10.18653\/v1\/2020.acl-main.663","article-title":"What are the goals of distributional semantics?","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Emerson","year":"2020"},{"issue":"10","key":"2025032113503891300_bib50","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1002\/lnco.362","article-title":"Vector space models of word meaning and phrase meaning: A survey","volume":"6","author":"Erk","year":"2012","journal-title":"Language and Linguistics Compass"},{"issue":"17","key":"2025032113503891300_bib51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3765\/sp.9.17","article-title":"What do you know about an alligator when you know the company it keeps?","volume":"9","author":"Erk","year":"2016","journal-title":"Semantics & Pragmatics"},{"key":"2025032113503891300_bib52","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1146\/annurev-linguistics-031120-015515","article-title":"The probabilistic turn in semantics and pragmatics","volume":"8","author":"Erk","year":"2022","journal-title":"Annual Review of Linguistics"},{"key":"2025032113503891300_bib53","doi-asserted-by":"publisher","first-page":"3297","DOI":"10.18653\/v1\/P19-1319","article-title":"Unraveling antonym\u2019s word vectors through a siamese-like network","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Etcheverry","year":"2019"},{"key":"2025032113503891300_bib54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cogsys.2020.04.002","article-title":"Measuring text similarity based on structure and word embedding","volume":"63","author":"Farouk","year":"2020","journal-title":"Cognitive Systems Research"},{"key":"2025032113503891300_bib55","doi-asserted-by":"publisher","first-page":"153","DOI":"10.3389\/frobt.2019.00153","article-title":"Symbolic, distributed, and distributional representations for natural language processing in the era of deep learning: A survey","volume":"6","author":"Ferrone","year":"2020","journal-title":"Frontiers in Robotics and AI"},{"key":"2025032113503891300_bib56","first-page":"155","article-title":"The importance of context in the evaluation of word embeddings: The effects of antonymy and polysemy","volume-title":"Proceedings of the 15th International Conference on Computational Semantics","author":"Fodor","year":"2023"},{"issue":"2","key":"2025032113503891300_bib57","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0010-0277(90)90014-B","article-title":"Connectionism and the problem of systematicity: Why Smolensky\u2019s solution doesn\u2019t work","volume":"35","author":"Fodor","year":"1990","journal-title":"Cognition"},{"issue":"1\u20132","key":"2025032113503891300_bib58","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/0010-0277(88)90031-5","article-title":"Connectionism and cognitive architecture: A critical analysis","volume":"28","author":"Fodor","year":"1988","journal-title":"Cognition"},{"key":"2025032113503891300_bib59","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1146\/annurev-psych-122216-011829","article-title":"Concepts and compositionality: In search of the brain\u2019s language of thought","volume":"71","author":"Frankland","year":"2020","journal-title":"Annual Review of Psychology"},{"issue":"1","key":"2025032113503891300_bib60","first-page":"25","article-title":"\u00dcber sinn und bedeutung","volume":"100","author":"Frege","year":"1892","journal-title":"Zeitschrift f\u00fcr Philosophie und philosophische Kritik"},{"key":"2025032113503891300_bib61","first-page":"71","article-title":"Foundations of formal semantics","author":"Gajewski","year":"2015"},{"issue":"11","key":"2025032113503891300_bib62","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","article-title":"Shortcut learning in deep neural networks","volume":"2","author":"Geirhos","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"2025032113503891300_bib63","first-page":"776","article-title":"Phrase similarity in humans and machines","volume-title":"Proceedings of the 37th Annual Conference of the Cognitive Science Society","author":"Gershman","year":"2015"},{"issue":"9","key":"2025032113503891300_bib64","doi-asserted-by":"publisher","first-page":"952","DOI":"10.1038\/s42256-023-00718-1","article-title":"Testing the limits of natural language models for predicting human language judgments","volume":"5","author":"Golan","year":"2023","journal-title":"Nature Machine Intelligence"},{"key":"2025032113503891300_bib65","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199734689.013.0010","article-title":"Similarity","volume-title":"The Oxford Handbook of Thinking and Reasoning","author":"Goldstone","year":"2012"},{"key":"2025032113503891300_bib66","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.knosys.2018.03.022","article-title":"Graph embedding techniques, applications, and performance: A survey","volume":"151","author":"Goyal","year":"2018","journal-title":"Knowledge-Based Systems"},{"key":"2025032113503891300_bib67","article-title":"Generating sequences with recurrent neural networks","author":"Graves","year":"2013","journal-title":"arXiv preprint arXiv:1308.0850"},{"key":"2025032113503891300_bib68","first-page":"1394","article-title":"Experimental support for a categorical compositional distributional model of meaning","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Grefenstette","year":"2011"},{"key":"2025032113503891300_bib69","article-title":"On the binding problem in artificial neural networks","author":"Greff","year":"2020","journal-title":"arXiv preprint arXiv:2012.05208"},{"key":"2025032113503891300_bib70","article-title":"Uncovering more shallow heuristics: Probing the natural language inference capacities of transformer-based pre-trained language models using syllogistic patterns","author":"Gubelmann","year":"2022","journal-title":"arXiv preprint arXiv:2201.07614"},{"key":"2025032113503891300_bib71","unstructured":"Gung, James\n          . 2020. SemParse VerbNet parser. https:\/\/github.com\/jgung\/verbnet-parser"},{"issue":"14","key":"2025032113503891300_bib72","doi-asserted-by":"publisher","first-page":"12946","DOI":"10.1609\/aaai.v35i14.17531","article-title":"BERT & family eat word salad: Experiments with text understanding","volume":"35","author":"Gupta","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2025032113503891300_bib73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45977-6","volume-title":"Compositionality and Concepts in Linguistics and Psychology","author":"Hampton","year":"2017"},{"key":"2025032113503891300_bib74","doi-asserted-by":"publisher","first-page":"54","DOI":"10.18653\/v1\/E17-1006","article-title":"Learning compositionality functions on word embeddings for modelling attribute meaning in adjective-noun phrases","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers","author":"Hartung","year":"2017"},{"issue":"5","key":"2025032113503891300_bib75","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"2025032113503891300_bib76","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1613\/jair.1.11674","article-title":"Compositionality decomposed: How do neural networks generalise?","volume":"67","author":"Hupkes","year":"2020","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2025032113503891300_bib77","first-page":"52","article-title":"Can large language models truly understand prompts? A case study with negated prompts","volume-title":"Transfer Learning for Natural Language Processing Workshop","author":"Jang","year":"2023"},{"key":"2025032113503891300_bib78","article-title":"Foundations and applications of Montague grammar: 8M part 1: Philosophy, framework, computer science","author":"Janssen","year":"1986"},{"key":"2025032113503891300_bib79","article-title":"Prompt packer: Deceiving LLMs through compositional instruction with hidden attacks","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv:2310.10077"},{"key":"2025032113503891300_bib80","first-page":"3158","article-title":"Butterfly effects in frame semantic parsing: Impact of data processing on model ranking","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Kabbach","year":"2018"},{"key":"2025032113503891300_bib81","first-page":"114","article-title":"Separating disambiguation from composition in distributional semantics","volume-title":"Proceedings of the Seventeenth Conference on Computational Natural Language Learning","author":"Kartsaklis","year":"2013"},{"key":"2025032113503891300_bib82","article-title":"An efficient recognition and syntax-analysis algorithm for context-free languages","author":"Kasami","year":"1966","journal-title":"Coordinated Science Laboratory Report no. R-257"},{"key":"2025032113503891300_bib83","first-page":"1132","article-title":"A generative theory of similarity","volume-title":"Proceedings of the 27th Annual Conference of the Cognitive Science Society","author":"Kemp","year":"2005"},{"key":"2025032113503891300_bib84","article-title":"Measuring compositional generalization: A comprehensive method on realistic data","author":"Keysers","year":"2019","journal-title":"arXiv preprint arXiv:1912.09713"},{"key":"2025032113503891300_bib85","doi-asserted-by":"publisher","first-page":"9087","DOI":"10.18653\/v1\/2020.emnlp-main.731","article-title":"COGS: A compositional generalization challenge based on semantic interpretation","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Kim","year":"2020"},{"key":"2025032113503891300_bib86","first-page":"1989","article-title":"From TreeBank to PropBank","volume-title":"LREC","author":"Kingsbury","year":"2002"},{"key":"2025032113503891300_bib87","doi-asserted-by":"publisher","first-page":"5729","DOI":"10.18653\/v1\/P19-1573","article-title":"Empirical linguistic study of sentence embeddings","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Krasnowska-Kiera\u015b","year":"2019"},{"key":"2025032113503891300_bib88","first-page":"2873","article-title":"Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks","volume-title":"International Conference on Machine Learning","author":"Lake","year":"2018"},{"key":"2025032113503891300_bib89","first-page":"611","article-title":"Human few-shot learning of compositional instructions","volume-title":"41st Annual Meeting of the Cognitive Science Society: Creativity+ Cognition+ Computation, CogSci 2019","author":"Lake","year":"2019"},{"issue":"2\u20133","key":"2025032113503891300_bib90","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1080\/01638539809545028","article-title":"An introduction to latent semantic analysis","volume":"25","author":"Landauer","year":"1998","journal-title":"Discourse Processes"},{"issue":"5","key":"2025032113503891300_bib91","doi-asserted-by":"publisher","first-page":"1202","DOI":"10.1111\/cogs.12414","article-title":"Grammaticality, acceptability, and probability: A probabilistic view of linguistic knowledge","volume":"41","author":"Lau","year":"2017","journal-title":"Cognitive Science"},{"key":"2025032113503891300_bib92","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1146\/annurev-linguistics-030514-125254","article-title":"Distributional models of word meaning","volume":"4","author":"Lenci","year":"2018","journal-title":"Annual Review of Linguistics"},{"key":"2025032113503891300_bib93","doi-asserted-by":"publisher","first-page":"106","DOI":"10.18653\/v1\/2022.gem-1.8","article-title":"Semantic similarity as a window into vector-and graph-based metrics","volume-title":"Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)","author":"Leung","year":"2022"},{"issue":"1","key":"2025032113503891300_bib94","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1146\/annurev-linguist-030514-125312","article-title":"Bringing machine learning and compositional semantics together","volume":"1","author":"Liang","year":"2015","journal-title":"Annual Review of Linguistics"},{"key":"2025032113503891300_bib95","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.bica.2016.10.005","article-title":"Conceptual spaces for cognitive architectures: A lingua franca for different levels of representation","volume":"19","author":"Lieto","year":"2017","journal-title":"Biologically Inspired Cognitive Architectures"},{"key":"2025032113503891300_bib96","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1146\/annurev-linguistics-032020-051035","article-title":"Syntactic structure from deep learning","volume":"7","author":"Linzen","year":"2021","journal-title":"Annual Review of Linguistics"},{"issue":"1","key":"2025032113503891300_bib97","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/s40747-022-00819-1","article-title":"Sentence part-enhanced BERT with respect to downstream tasks","volume":"9","author":"Liu","year":"2023","journal-title":"Complex & Intelligent Systems"},{"key":"2025032113503891300_bib98","doi-asserted-by":"publisher","first-page":"108","DOI":"10.18653\/v1\/W18-5413","article-title":"Rearranging the familiar: Testing compositional generalization in recurrent networks","volume-title":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","author":"Loula","year":"2018"},{"issue":"6","key":"2025032113503891300_bib99","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1080\/09515089.2017.1296941","article-title":"Abstract concepts, compositionality, and the contextualism-invariantism debate","volume":"30","author":"L\u00f6hr","year":"2017","journal-title":"Philosophical Psychology"},{"issue":"48","key":"2025032113503891300_bib100","doi-asserted-by":"publisher","first-page":"30046","DOI":"10.1073\/pnas.1907367117","article-title":"Emergent linguistic structure in artificial neural networks trained by self-supervision","volume":"117","author":"Manning","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2025032113503891300_bib101","first-page":"216","article-title":"A sick cure for the evaluation of compositional distributional semantic models","volume-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914)","author":"Marelli","year":"2014"},{"issue":"1791","key":"2025032113503891300_bib102","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1098\/rstb.2019.0298","article-title":"Modelling meaning composition from formalism to mechanism","volume":"375","author":"Martin","year":"2020","journal-title":"Philosophical Transactions of the Royal Society B"},{"issue":"1791","key":"2025032113503891300_bib103","doi-asserted-by":"publisher","first-page":"20190306","DOI":"10.1098\/rstb.2019.0306","article-title":"Tensors and compositionality in neural systems","volume":"375","author":"Martin","year":"2020","journal-title":"Philosophical Transactions of the Royal Society B"},{"issue":"42","key":"2025032113503891300_bib104","doi-asserted-by":"publisher","first-page":"25966","DOI":"10.1073\/pnas.1910416117","article-title":"Placing language in an integrated understanding system: Next steps toward human-level performance in neural language models","volume":"117","author":"McClelland","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2025032113503891300_bib105","doi-asserted-by":"publisher","first-page":"217","DOI":"10.18653\/v1\/2020.blackboxnlp-1.21","article-title":"BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance","volume-title":"Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP","author":"McCoy","year":"2020"},{"key":"2025032113503891300_bib106","first-page":"409","article-title":"Deeper syntax for better semantic parsing","volume-title":"COLING 2016-26th International Conference on Computational Linguistics","author":"Michalon","year":"2016"},{"key":"2025032113503891300_bib107","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"Mikolov","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"8","key":"2025032113503891300_bib108","doi-asserted-by":"publisher","first-page":"1388","DOI":"10.1111\/j.1551-6709.2010.01106.x","article-title":"Composition in distributional models of semantics","volume":"34","author":"Mitchell","year":"2010","journal-title":"Cognitive Science"},{"key":"2025032113503891300_bib109","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1111\/j.1755-2567.1970.tb00434.x","article-title":"Universal grammar","volume":"36","author":"Montague","year":"1970","journal-title":"Theoria"},{"key":"2025032113503891300_bib110","doi-asserted-by":"publisher","first-page":"4885","DOI":"10.18653\/v1\/2020.acl-main.441","article-title":"Adversarial NLI: A new benchmark for natural language understanding","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Nie","year":"2020"},{"key":"2025032113503891300_bib111","doi-asserted-by":"publisher","first-page":"4658","DOI":"10.18653\/v1\/P19-1459","article-title":"Probing neural network comprehension of natural language arguments","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Niven","year":"2019"},{"key":"2025032113503891300_bib112","doi-asserted-by":"publisher","first-page":"3591","DOI":"10.18653\/v1\/2022.acl-long.251","article-title":"Making transformers solve compositional tasks","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Ontanon","year":"2022"},{"key":"2025032113503891300_bib113","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1162\/tacl_a_00435","article-title":"Weisfeiler-Leman in the Bamboo: Novel AMR graph metrics and a benchmark for AMR graph similarity","volume":"9","author":"Opitz","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2025032113503891300_bib114","first-page":"625","article-title":"SBERT studies meaning representations: Decomposing sentence embeddings into explainable semantic features","volume-title":"Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing","author":"Opitz","year":"2022"},{"issue":"4","key":"2025032113503891300_bib115","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2537046","article-title":"A new benchmark dataset with production methodology for short text semantic similarity algorithms","volume":"10","author":"O\u2019shea","year":"2014","journal-title":"ACM Transactions on Speech and Language Processing (TSLP)"},{"key":"2025032113503891300_bib116","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"2025032113503891300_bib117","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1162\/coli.2007.33.2.161","article-title":"Dependency-based construction of semantic space models","volume":"33","author":"Pad\u00f3","year":"2007","journal-title":"Computational Linguistics"},{"issue":"3","key":"2025032113503891300_bib118","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1111\/j.1747-9991.2009.00228.x","article-title":"Compositionality I: Definitions and variants","volume":"5","author":"Pagin","year":"2010","journal-title":"Philosophy Compass"},{"key":"2025032113503891300_bib119","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1093\/oxfordhb\/9780199842193.013.15","article-title":"VerbNet: Capturing English verb behavior, meaning, and usage","author":"Palmer","year":"2016","journal-title":"The Oxford Handbook of Cognitive Science"},{"key":"2025032113503891300_bib120","doi-asserted-by":"publisher","first-page":"424","DOI":"10.18653\/v1\/2022.acl-short.46","article-title":"Revisiting the compositional generalization abilities of neural sequence models","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Patel","year":"2022"},{"key":"2025032113503891300_bib121","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1146\/annurev-linguistics-031120-122924","article-title":"Semantic structure in deep learning","volume":"8","author":"Pavlick","year":"2022","journal-title":"Annual Review of Linguistics"},{"key":"2025032113503891300_bib122","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-319-45977-6_3","article-title":"Compositionality and concepts\u2014A perspective from formal semantics and philosophy of language","author":"Pelletier","year":"2017","journal-title":"Compositionality and Concepts in Linguistics and Psychology"},{"key":"2025032113503891300_bib123","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.3389\/fpsyg.2017.01806","article-title":"Beyond verb meaning: Experimental evidence for incremental processing of semantic roles and event structure","volume":"8","author":"Philipp","year":"2017","journal-title":"Frontiers in Psychology"},{"key":"2025032113503891300_bib124","doi-asserted-by":"publisher","first-page":"4609","DOI":"10.18653\/v1\/2020.acl-main.420","article-title":"Information-theoretic probing for linguistic structure","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Pimentel","year":"2020"},{"key":"2025032113503891300_bib125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.85","article-title":"Is ChatGPT a general-purpose natural language processing task solver?","author":"Qin","year":"2023","journal-title":"arXiv preprint arXiv:2302.06476"},{"key":"2025032113503891300_bib126","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11431-020-1647-3","article-title":"Pre-trained models for natural language processing: A survey","author":"Qiu","year":"2020","journal-title":"Science China Technological Sciences"},{"key":"2025032113503891300_bib127","doi-asserted-by":"publisher","first-page":"994","DOI":"10.26615\/978-954-452-056-4_115","article-title":"Enhancing unsupervised sentence similarity methods with deep contextualised word representations","volume-title":"Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)","author":"Ranasinghe","year":"2019"},{"key":"2025032113503891300_bib128","unstructured":"Reimers, Nils\n          . 2021. Sentence-transformers. https:\/\/github.com\/UKPLab\/sentence-transformers\/"},{"key":"2025032113503891300_bib129","doi-asserted-by":"publisher","first-page":"3982","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Reimers","year":"2019"},{"key":"2025032113503891300_bib130","doi-asserted-by":"publisher","first-page":"4902","DOI":"10.18653\/v1\/2020.acl-main.442","article-title":"Beyond accuracy: Behavioral testing of NLP models with checklist","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Ribeiro","year":"2020"},{"issue":"2","key":"2025032113503891300_bib131","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3424672","article-title":"Knowledge graph embedding for link prediction: A comparative analysis","volume":"15","author":"Rossi","year":"2021","journal-title":"ACM Transactions on Knowledge Discovery from Data (TKDD)"},{"key":"2025032113503891300_bib132","doi-asserted-by":"publisher","first-page":"977","DOI":"10.3115\/v1\/N15-1099","article-title":"A word embedding approach to predicting the compositionality of multiword expressions","volume-title":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Salehi","year":"2015"},{"key":"2025032113503891300_bib133","doi-asserted-by":"publisher","first-page":"922","DOI":"10.18653\/v1\/2021.acl-long.75","article-title":"Compositional generalization and natural language variation: Can a semantic parsing approach handle both?","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Shaw","year":"2021"},{"key":"2025032113503891300_bib134","first-page":"31210","article-title":"Large language models can be easily distracted by irrelevant context","volume-title":"International Conference on Machine Learning","author":"Shi","year":"2023"},{"key":"2025032113503891300_bib135","doi-asserted-by":"publisher","first-page":"4631","DOI":"10.18653\/v1\/D18-1492","article-title":"On tree-based neural sentence modeling","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Shi","year":"2018"},{"key":"2025032113503891300_bib136","doi-asserted-by":"publisher","first-page":"267","DOI":"10.18653\/v1\/2022.naacl-srw.33","article-title":"Unifying parsing and tree-structured models for generating sentence semantic representations","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop","author":"Simoulin","year":"2022"},{"issue":"3","key":"2025032113503891300_bib137","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1002\/aaai.12065","article-title":"Neurocompositional computing: From the central paradox of cognition to a new generation of AI systems","volume":"43","author":"Smolensky","year":"2022","journal-title":"AI Magazine"},{"key":"2025032113503891300_bib138","first-page":"1201","article-title":"Semantic compositionality through recursive matrix-vector spaces","volume-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning","author":"Socher","year":"2012"},{"key":"2025032113503891300_bib139","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.blackboxnlp-1.23","article-title":"Discovering the compositional structure of vector representations with role learning networks","author":"Soulos","year":"2019","journal-title":"arXiv preprint arXiv:1910.09113"},{"key":"2025032113503891300_bib140","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2022","journal-title":"arXiv preprint arXiv:2206.04615"},{"key":"2025032113503891300_bib141","first-page":"596","article-title":"Compositionality and biologically plausible models","author":"Stewart","year":"2009","journal-title":"The Oxford Handbook of Compositionality"},{"key":"2025032113503891300_bib142","article-title":"Whitening sentence representations for better semantics and faster retrieval","author":"Su","year":"2021","journal-title":"arXiv preprint arXiv:2103.15316"},{"issue":"05","key":"2025032113503891300_bib143","doi-asserted-by":"publisher","first-page":"8968","DOI":"10.1609\/aaai.v34i05.6428","article-title":"ERNIE 2.0: A continual pre-training framework for language understanding","volume":"34","author":"Sun","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2025032113503891300_bib144","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1093\/oxfordhb\/9780199541072.013.0003","article-title":"The case for compositionality","author":"Szab\u00f3","year":"2012","journal-title":"The Oxford Handbook of Compositionality"},{"key":"2025032113503891300_bib145","article-title":"Compositionality","author":"Szab\u00f3","year":"2020","journal-title":"The Stanford Encyclopedia of Philosophy"},{"key":"2025032113503891300_bib146","doi-asserted-by":"publisher","first-page":"4527","DOI":"10.18653\/v1\/2021.emnlp-main.372","article-title":"All bark and no bite: Rogue dimensions in transformer language models obscure representational quality","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Timkey","year":"2021"},{"key":"2025032113503891300_bib147","doi-asserted-by":"publisher","first-page":"100433","DOI":"10.1016\/j.cosrev.2021.100433","article-title":"Comprehensive analysis of embeddings and pre-training in NLP","volume":"42","author":"Tripathy","year":"2021","journal-title":"Computer Science Review"},{"key":"2025032113503891300_bib148","doi-asserted-by":"publisher","first-page":"411","DOI":"10.18653\/v1\/2021.acl-short.52","article-title":"DefSent: Sentence embeddings using definition sentences","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)","author":"Tsukagoshi","year":"2021"},{"issue":"1791","key":"2025032113503891300_bib149","doi-asserted-by":"publisher","first-page":"20190309","DOI":"10.1098\/rstb.2019.0309","article-title":"Training neural networks to encode symbols enables combinatorial generalization","volume":"375","author":"Vankov","year":"2020","journal-title":"Philosophical Transactions of the Royal Society B"},{"key":"2025032113503891300_bib150","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"2025032113503891300_bib151","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1111\/cogs.12330","article-title":"Spicy adjectives and nominal donkeys: Capturing semantic deviance using compositionality in distributional spaces","volume":"41","author":"Vecchi","year":"2017","journal-title":"Cognitive Science"},{"key":"2025032113503891300_bib152","doi-asserted-by":"crossref","first-page":"6060","DOI":"10.18653\/v1\/2022.acl-long.419","article-title":"Just rank: Rethinking evaluation with word and sentence similarities","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Wang","year":"2022"},{"key":"2025032113503891300_bib153","doi-asserted-by":"publisher","first-page":"e19","DOI":"10.1017\/ATSIP.2019.12","article-title":"Evaluating word embedding models: Methods and experimental results","volume":"8","author":"Wang","year":"2019","journal-title":"APSIPA Transactions on Signal and Information Processing"},{"key":"2025032113503891300_bib154","article-title":"Adversarial demonstration attacks on large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2305.14950"},{"key":"2025032113503891300_bib155","doi-asserted-by":"publisher","first-page":"117084","DOI":"10.1016\/j.eswa.2022.117084","article-title":"A joint FrameNet and element focusing sentence-BERT method of sentence similarity computation","volume":"200","author":"Wang","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"2025032113503891300_bib156","first-page":"1340","article-title":"Sentence similarity learning by lexical decomposition and composition","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers","author":"Wang","year":"2016"},{"key":"2025032113503891300_bib157","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1162\/tacl_a_00321","article-title":"BLiMP: The benchmark of linguistic minimal pairs for English","volume":"8","author":"Warstadt","year":"2020","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2025032113503891300_bib158","doi-asserted-by":"publisher","first-page":"2300","DOI":"10.18653\/v1\/2022.naacl-main.167","article-title":"Do prompt-based models really understand the meaning of their prompts?","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Webson","year":"2022"},{"key":"2025032113503891300_bib159","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.patrec.2023.04.012","article-title":"SynWMD: Syntax-aware word mover\u2019s distance for sentence similarity evaluation","volume":"170","author":"Wei","year":"2023","journal-title":"Pattern Recognition Letters"},{"key":"2025032113503891300_bib160","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1023\/A:1005401829598","article-title":"On mathematical proofs of the vacuity of compositionality","author":"Westerst\u00e5hl","year":"1998","journal-title":"Linguistics and Philosophy"},{"key":"2025032113503891300_bib161","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.337","article-title":"Structural generalization is hard for sequence-to-sequence models","author":"Yao","year":"2022","journal-title":"arXiv preprint arXiv:2210.13050"},{"issue":"3","key":"2025032113503891300_bib162","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","article-title":"Recent trends in deep learning based natural language processing","volume":"13","author":"Young","year":"2018","journal-title":"IEEE Computational Intelligence Magazine"},{"key":"2025032113503891300_bib163","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.684","article-title":"An empirical revisiting of linguistic knowledge fusion in language understanding tasks","author":"Yu","year":"2022","journal-title":"arXiv preprint arXiv:2210.13002"},{"key":"2025032113503891300_bib164","doi-asserted-by":"publisher","first-page":"4896","DOI":"10.18653\/v1\/2020.emnlp-main.397","article-title":"Assessing phrasal representation and composition in transformers","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Yu","year":"2020"},{"issue":"3","key":"2025032113503891300_bib165","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1162\/coli_a_00385","article-title":"Sentence meaning representations across languages: What can we learn from existing frameworks?","volume":"46","author":"\u017dabokrtsky\u0300","year":"2020","journal-title":"Computational Linguistics"},{"key":"2025032113503891300_bib166","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/BF00985572","article-title":"From compositional to systematic semantics","volume":"17","author":"Zadrozny","year":"1994","journal-title":"Linguistics and Philosophy"},{"key":"2025032113503891300_bib167","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/375","article-title":"On the paradox of learning to reason from data","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2205.11502"},{"issue":"10","key":"2025032113503891300_bib168","doi-asserted-by":"publisher","first-page":"1898","DOI":"10.1007\/s11431-020-1666-4","article-title":"A survey of syntactic-semantic parsing based on constituent and dependency structures","volume":"63","author":"Zhang","year":"2020","journal-title":"Science China Technological Sciences"},{"issue":"05","key":"2025032113503891300_bib169","doi-asserted-by":"publisher","first-page":"9628","DOI":"10.1609\/aaai.v34i05.6510","article-title":"Semantics-aware BERT for language understanding","volume":"34","author":"Zhang","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2025032113503891300_bib170","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022","journal-title":"arXiv preprint arXiv:2205.10625"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/51\/1\/139\/2479680\/coli_a_00536.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/51\/1\/139\/2479680\/coli_a_00536.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T18:03:50Z","timestamp":1742580230000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/51\/1\/139\/124463\/Compositionality-and-Sentence-Meaning-Comparing"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":170,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3,15]]},"published-print":{"date-parts":[[2025,3,15]]}},"URL":"https:\/\/doi.org\/10.1162\/coli_a_00536","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]}}}