{"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/2407-21489","title":"Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends","arxiv_id":"2407.21489","date":"2024-07-31","proceeding":null,"authors":["Giuliano Martinelli","Edoardo Barba","Roberto Navigli"],"abstract":"Large autoregressive generative models have emerged as the cornerstone for achieving the highest performance across several Natural Language Processing tasks. However, the urge to attain superior results has, at times, led to the premature replacement of carefully designed task-specific approaches without exhaustive experimentation. The Coreference Resolution task is no exception; all recent state-of-the-art solutions adopt large generative autoregressive models that outperform encoder-based discriminative systems. In this work,we challenge this recent trend by introducing Maverick, a carefully designed - yet simple - pipeline, which enables running a state-of-the-art Coreference Resolution system within the constraints of an academic budget, outperforming models with up to 13 billion parameters with as few as 500 million parameters. Maverick achieves state-of-the-art performance on the CoNLL-2012 benchmark, training with up to 0.006x the memory resources and obtaining a 170x faster inference compared to previous state-of-the-art systems. We extensively validate the robustness of the Maverick framework with an array of diverse experiments, reporting improvements over prior systems in data-scarce, long-document, and out-of-domain settings. We release our code and models for research purposes at https://github.com/SapienzaNLP/maverick-coref.","url_abs":"https://arxiv.org/abs/2407.21489v1","url_pdf":"https://arxiv.org/pdf/2407.21489v1.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":"2407-21489","repo_url":"https://github.com/sapienzanlp/maverick-coref","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/coreference-resolution-on-conll-2012","task":"Coreference Resolution","dataset":"CoNLL 2012","model":"Maverick_mes","rank_in_archive_order":1,"of":18,"metrics":{"Avg F1":"83.6"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-gap-1","task":"Coreference Resolution","dataset":"GAP","model":"Maverick_incr","rank_in_archive_order":3,"of":5,"metrics":{"Overall F1":"91.2"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-litbank","task":"Coreference Resolution","dataset":"LitBank","model":"Maverick_incr","rank_in_archive_order":1,"of":2,"metrics":{"Avg F1":"78.3"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-ontonotes","task":"Coreference Resolution","dataset":"OntoNotes","model":"Maverick_mes","rank_in_archive_order":1,"of":26,"metrics":{"F1":"83.6"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-preco","task":"Coreference Resolution","dataset":"PreCo","model":"Maverick_incr","rank_in_archive_order":1,"of":2,"metrics":{"F1":"88.0"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-wikicoref","task":"Coreference Resolution","dataset":"WikiCoref","model":"Maverick_mes","rank_in_archive_order":1,"of":3,"metrics":{"F1":"66.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.21489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21489"}},"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":"deterministic:regex_extraction","url":"https://github.com/SapienzaNLP/maverick-coref","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":2,"ran":3,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"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":11,"samples":[{"code_sha256_prefix":"20922c79a0929bbf","entry":"flatten","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/common/util.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/common/util.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"20922c79a0929bbf"}},{"code_sha256_prefix":"6b7799612a72d501","entry":"A_and_B_corefs","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/evaluate.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6b7799612a72d501"}},{"code_sha256_prefix":"fef6da1366efc239","entry":"candidate_pronoun_clustered","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/evaluate.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fef6da1366efc239"}},{"code_sha256_prefix":"197c9d892060fc72","entry":"find_offsets_in_clusters","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/evaluate.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"197c9d892060fc72"}},{"code_sha256_prefix":"9910e2fc297f8665","entry":"identity","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/utils/sampler.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/utils/sampler.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9910e2fc297f8665"}},{"code_sha256_prefix":"e8ce0142bdf8a593","entry":"b_cubed","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/common/metrics.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/common/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8ce0142bdf8a593"}},{"code_sha256_prefix":"5dc251a1bb16c94f","entry":"f1","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/common/metrics.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/common/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5dc251a1bb16c94f"}},{"code_sha256_prefix":"f2c593891a325316","entry":"get_category_id","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/common/util.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/common/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f2c593891a325316"}},{"code_sha256_prefix":"00efd68da46bd738","entry":"get_logger","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/utils/logging.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/utils/logging.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"00efd68da46bd738"}},{"code_sha256_prefix":"72038039c3ad8d52","entry":"get_pronoun_id","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/common/util.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/common/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"72038039c3ad8d52"}},{"code_sha256_prefix":"8b30464b3ec47d85","entry":"muc","repo":"SapienzaNLP/maverick-coref","repo_kind":"official","path":"maverick/common/metrics.py","file_url":"https://github.com/SapienzaNLP/maverick-coref/blob/HEAD/maverick/common/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8b30464b3ec47d85"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}