{"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/fast-and-accurate-entity-recognition-with","title":"Fast and Accurate Entity Recognition with Iterated Dilated Convolutions","arxiv_id":"1702.02098","date":"2017-02-07","proceeding":"EMNLP 2017 9","authors":["Emma Strubell","Patrick Verga","David Belanger","Andrew McCallum"],"abstract":"Today when many practitioners run basic NLP on the entire web and\nlarge-volume traffic, faster methods are paramount to saving time and energy\ncosts. Recent advances in GPU hardware have led to the emergence of\nbi-directional LSTMs as a standard method for obtaining per-token vector\nrepresentations serving as input to labeling tasks such as NER (often followed\nby prediction in a linear-chain CRF). Though expressive and accurate, these\nmodels fail to fully exploit GPU parallelism, limiting their computational\nefficiency. This paper proposes a faster alternative to Bi-LSTMs for NER:\nIterated Dilated Convolutional Neural Networks (ID-CNNs), which have better\ncapacity than traditional CNNs for large context and structured prediction.\nUnlike LSTMs whose sequential processing on sentences of length N requires O(N)\ntime even in the face of parallelism, ID-CNNs permit fixed-depth convolutions\nto run in parallel across entire documents. We describe a distinct combination\nof network structure, parameter sharing and training procedures that enable\ndramatic 14-20x test-time speedups while retaining accuracy comparable to the\nBi-LSTM-CRF. Moreover, ID-CNNs trained to aggregate context from the entire\ndocument are even more accurate while maintaining 8x faster test time speeds.","url_abs":"http://arxiv.org/abs/1702.02098v3","url_pdf":"http://arxiv.org/pdf/1702.02098v3.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":"fast-and-accurate-entity-recognition-with","repo_url":"https://github.com/iesl/dilated-cnn-ner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"fast-and-accurate-entity-recognition-with","repo_url":"https://github.com/Tuofengalways/ee_Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fast-and-accurate-entity-recognition-with","repo_url":"https://github.com/john-hewitt/conditional-probing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-and-accurate-entity-recognition-with","repo_url":"https://github.com/zjuym/chinese_cws_ner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-ner-on-ontonotes-v5","task":"Named Entity Recognition (NER)","dataset":"Ontonotes v5 (English)","model":"BiLSTM-CRF","rank_in_archive_order":25,"of":28,"metrics":{"F1":"86.99"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-ontonotes-v5","task":"Named Entity Recognition (NER)","dataset":"Ontonotes v5 (English)","model":"Iterated Dilated CNN","rank_in_archive_order":26,"of":28,"metrics":{"F1":"86.84"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.02098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02098"}},"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/zjuym/chinese_cws_ner","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iesl/dilated-cnn-ner","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Tuofengalways/ee_Model","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/john-hewitt/conditional-probing","reach":null}],"summary":{"ran_violates":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"3ef079be3da0b68a","entry":"is_background","repo":"iesl/dilated-cnn-ner","repo_kind":"official","path":"src/eval_f1.py","file_url":"https://github.com/iesl/dilated-cnn-ner/blob/HEAD/src/eval_f1.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ef079be3da0b68a"}},{"code_sha256_prefix":"af722a1af81adfbb","entry":"is_continue","repo":"iesl/dilated-cnn-ner","repo_kind":"official","path":"src/eval_f1.py","file_url":"https://github.com/iesl/dilated-cnn-ner/blob/HEAD/src/eval_f1.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"af722a1af81adfbb"}},{"code_sha256_prefix":"df07c60c27dd08a1","entry":"is_start","repo":"iesl/dilated-cnn-ner","repo_kind":"official","path":"src/eval_f1.py","file_url":"https://github.com/iesl/dilated-cnn-ner/blob/HEAD/src/eval_f1.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df07c60c27dd08a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}