{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/targeted-syntactic-evaluation-of-language","title":"Targeted Syntactic Evaluation of Language Models","arxiv_id":"1808.09031","date":"2018-08-27","proceeding":"EMNLP 2018 10","authors":["Rebecca Marvin","Tal Linzen"],"abstract":"We present a dataset for evaluating the grammaticality of the predictions of\na language model. We automatically construct a large number of minimally\ndifferent pairs of English sentences, each consisting of a grammatical and an\nungrammatical sentence. The sentence pairs represent different variations of\nstructure-sensitive phenomena: subject-verb agreement, reflexive anaphora and\nnegative polarity items. We expect a language model to assign a higher\nprobability to the grammatical sentence than the ungrammatical one. In an\nexperiment using this data set, an LSTM language model performed poorly on many\nof the constructions. Multi-task training with a syntactic objective (CCG\nsupertagging) improved the LSTM's accuracy, but a large gap remained between\nits performance and the accuracy of human participants recruited online. This\nsuggests that there is considerable room for improvement over LSTMs in\ncapturing syntax in a language model.","url_abs":"http://arxiv.org/abs/1808.09031v1","url_pdf":"http://arxiv.org/pdf/1808.09031v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"targeted-syntactic-evaluation-of-language","repo_url":"https://github.com/BeckyMarvin/LM_syneval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"targeted-syntactic-evaluation-of-language","repo_url":"https://github.com/huggingface/bert-syntax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"targeted-syntactic-evaluation-of-language","repo_url":"https://github.com/icewing1996/bert-syntax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"targeted-syntactic-evaluation-of-language","repo_url":"https://github.com/jennhu/reflexive-anaphor-licensing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"targeted-syntactic-evaluation-of-language","repo_url":"https://github.com/yoavg/bert-syntax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"ccg-supertagging","task_name":"CCG Supertagging"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.09031"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BeckyMarvin/LM_syneval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/icewing1996/bert-syntax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yoavg/bert-syntax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/bert-syntax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jennhu/reflexive-anaphor-licensing","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3353a6ec1c61c55e","entry":"bysize","repo":"huggingface/bert-syntax","repo_kind":"listed","path":"inflect.py","file_url":"https://github.com/huggingface/bert-syntax/blob/HEAD/inflect.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3353a6ec1c61c55e"}},{"code_sha256_prefix":"29f4fc274ae5a1ef","entry":"enclose","repo":"huggingface/bert-syntax","repo_kind":"listed","path":"inflect.py","file_url":"https://github.com/huggingface/bert-syntax/blob/HEAD/inflect.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"29f4fc274ae5a1ef"}},{"code_sha256_prefix":"da43f58c32d1efdf","entry":"is_more_probable","repo":"BeckyMarvin/LM_syneval","repo_kind":"official","path":"src/analyze_results.py","file_url":"https://github.com/BeckyMarvin/LM_syneval/blob/HEAD/src/analyze_results.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da43f58c32d1efdf"}},{"code_sha256_prefix":"cd4bb876b230ebb2","entry":"joinstem","repo":"huggingface/bert-syntax","repo_kind":"listed","path":"inflect.py","file_url":"https://github.com/huggingface/bert-syntax/blob/HEAD/inflect.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd4bb876b230ebb2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}