{"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/a-joint-many-task-model-growing-a-neural","title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks","arxiv_id":"1611.01587","date":"2016-11-05","proceeding":"EMNLP 2017 9","authors":["Kazuma Hashimoto","Caiming Xiong","Yoshimasa Tsuruoka","Richard Socher"],"abstract":"Transfer and multi-task learning have traditionally focused on either a\nsingle source-target pair or very few, similar tasks. Ideally, the linguistic\nlevels of morphology, syntax and semantics would benefit each other by being\ntrained in a single model. We introduce a joint many-task model together with a\nstrategy for successively growing its depth to solve increasingly complex\ntasks. Higher layers include shortcut connections to lower-level task\npredictions to reflect linguistic hierarchies. We use a simple regularization\nterm to allow for optimizing all model weights to improve one task's loss\nwithout exhibiting catastrophic interference of the other tasks. Our single\nend-to-end model obtains state-of-the-art or competitive results on five\ndifferent tasks from tagging, parsing, relatedness, and entailment tasks.","url_abs":"http://arxiv.org/abs/1611.01587v5","url_pdf":"http://arxiv.org/pdf/1611.01587v5.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":"a-joint-many-task-model-growing-a-neural","repo_url":"https://github.com/hassyGo/charNgram2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-joint-many-task-model-growing-a-neural","repo_url":"https://github.com/rubythonode/joint-many-task-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/chunking-on-penn-treebank","task":"Chunking","dataset":"Penn Treebank","model":"JMT","rank_in_archive_order":3,"of":8,"metrics":{"F1 score":"95.77"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.01587","atlas_url":"https://app.syntology.ai/?focus=1611.01587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01587"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/rubythonode/joint-many-task-model","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hassyGo/charNgram2vec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"50f3532ff1835fba","entry":"split","repo":"rubythonode/joint-many-task-model","repo_kind":"listed","path":"data.py","file_url":"https://github.com/rubythonode/joint-many-task-model/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50f3532ff1835fba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}