{"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/2408-03125","title":"COMMENTATOR: A Code-mixed Multilingual Text Annotation Framework","arxiv_id":"2408.03125","date":"2024-08-06","proceeding":null,"authors":["Rajvee Sheth","Shubh Nisar","Heenaben Prajapati","Himanshu Beniwal","Mayank Singh"],"abstract":"As the NLP community increasingly addresses challenges associated with multilingualism, robust annotation tools are essential to handle multilingual datasets efficiently. In this paper, we introduce a code-mixed multilingual text annotation framework, COMMENTATOR, specifically designed for annotating code-mixed text. The tool demonstrates its effectiveness in token-level and sentence-level language annotation tasks for Hinglish text. We perform robust qualitative human-based evaluations to showcase COMMENTATOR led to 5x faster annotations than the best baseline. Our code is publicly available at \\url{https://github.com/lingo-iitgn/commentator}. The demonstration video is available at \\url{https://bit.ly/commentator_video}.","url_abs":"https://arxiv.org/abs/2408.03125v1","url_pdf":"https://arxiv.org/pdf/2408.03125v1.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":"2408-03125","repo_url":"https://github.com/lingo-iitgn/commentator","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-annotation","task_name":"text annotation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.03125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03125"}},"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/sagorbrur/codeswitch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/lingo-iitgn/commentator","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/microsoft/LID-tool","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":12},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"found_in_text":{"samples":10,"ran":2,"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":"56ee6effc1a57764","entry":"blurb2Dict","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56ee6effc1a57764"}},{"code_sha256_prefix":"79faeb3291c4c81c","entry":"genUID","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79faeb3291c4c81c"}},{"code_sha256_prefix":"a244ad6d68c2825e","entry":"callMallet","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"a244ad6d68c2825e"}},{"code_sha256_prefix":"0aafd067c51639c2","entry":"callMallet","repo":"lingo-iitgn/commentator","repo_kind":"official","path":"backend/LID_tool/getLanguage.py","file_url":"https://github.com/lingo-iitgn/commentator/blob/HEAD/backend/LID_tool/getLanguage.py","link_basis":"first_harvest_node","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":"0aafd067c51639c2"}},{"code_sha256_prefix":"2eeaa80c3bf6ca58","entry":"createDicts","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"2eeaa80c3bf6ca58"}},{"code_sha256_prefix":"9476aad9d7227acf","entry":"createDicts","repo":"lingo-iitgn/commentator","repo_kind":"official","path":"backend/LID_tool/getLanguage.py","file_url":"https://github.com/lingo-iitgn/commentator/blob/HEAD/backend/LID_tool/getLanguage.py","link_basis":"first_harvest_node","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":"9476aad9d7227acf"}},{"code_sha256_prefix":"113706d529c0e812","entry":"dictLookup","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"113706d529c0e812"}},{"code_sha256_prefix":"cd0f026b83346c87","entry":"dictTagging","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"cd0f026b83346c87"}},{"code_sha256_prefix":"2ea9f8174f2ecadf","entry":"langIdentify","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"2ea9f8174f2ecadf"}},{"code_sha256_prefix":"eb1950f0d466f228","entry":"langIdentify","repo":"lingo-iitgn/commentator","repo_kind":"official","path":"backend/LID_tool/getLanguage.py","file_url":"https://github.com/lingo-iitgn/commentator/blob/HEAD/backend/LID_tool/getLanguage.py","link_basis":"first_harvest_node","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":"eb1950f0d466f228"}},{"code_sha256_prefix":"3f5c1395f67bc805","entry":"memoizeWord","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"3f5c1395f67bc805"}},{"code_sha256_prefix":"8c20c664b8abcc90","entry":"mergeBlurbs","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"8c20c664b8abcc90"}},{"code_sha256_prefix":"f97ab636e79cd91e","entry":"readConfig","repo":"microsoft/LID-tool","repo_kind":"found_in_text","path":"getLanguage.py","file_url":"https://github.com/microsoft/LID-tool/blob/HEAD/getLanguage.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":"f97ab636e79cd91e"}},{"code_sha256_prefix":"dee05029bda91008","entry":"readConfig","repo":"lingo-iitgn/commentator","repo_kind":"official","path":"backend/LID_tool/getLanguage.py","file_url":"https://github.com/lingo-iitgn/commentator/blob/HEAD/backend/LID_tool/getLanguage.py","link_basis":"first_harvest_node","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":"dee05029bda91008"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}