{"doi":"10.18653/v1/2020.acl-main.158","title":"A Systematic Assessment of Syntactic Generalization in Neural Language Models","abstract":"While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic knowledge. Furthermore, existing work has not provided a clear picture about the model properties required to produce proper syntactic generalizations. We present a systematic evaluation of the syntactic knowledge of neural language models, testing 20 combinations of model types and data sizes on a set of 34 English-language syntactic test suites. We find substantial differences in syntactic generalization performance by model architecture, with sequential models underperforming other architectures. Factorially manipulating model architecture and training dataset size (1M-40M words), we find that variability in syntactic generalization performance is substantially greater by architecture than by dataset size for the corpora tested in our experiments. Our results also reveal a dissociation between perplexity and syntactic generalization performance.","journal":null,"year":2020,"id":118300,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":128,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9503,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":550254,"name":"Jon Gauthier","orcid":"0000-0002-6118-5833","position":1,"is_corresponding":false},{"id":274012,"name":"Peng Qian","orcid":"0000-0003-4934-5811","position":2,"is_corresponding":false},{"id":550255,"name":"Ethan Wilcox","orcid":"0000-0002-5128-9890","position":3,"is_corresponding":false},{"id":369882,"name":"Roger Lévy","orcid":"0000-0002-4493-8864","position":4,"is_corresponding":false},{"id":289581,"name":"Jennifer Hu","orcid":"0000-0002-6049-7595","position":0,"is_corresponding":true}],"reference_count":70,"raw_metadata":null,"created_at":"2026-07-18T23:13:58.531532Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}