{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EU4GO3IVV73PJ6RMHY7HMSYFPM","short_pith_number":"pith:EU4GO3IV","schema_version":"1.0","canonical_sha256":"2538676d15aff6f4fa2c3e3e764b057b2db466e6b8137ca222a46fca1b25b336","source":{"kind":"arxiv","id":"2108.03867","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Multi-Task Learning for Sentiment Analysis and Offensive Language Identification in Under-Resourced Dravidian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CC","authors_text":"Adeep Hande, Bharathi Raja Chakravarthi, Prasanna Kumar Kumaresan, Rahul Ponnusamy, Ruba Priyadharshini, Sajeetha Thavareesan, Siddhanth U Hegde","submitted_at":"2021-08-09T08:26:17Z","abstract_excerpt":"To obtain extensive annotated data for under-resourced languages is challenging, so in this research, we have investigated whether it is beneficial to train models using multi-task learning. Sentiment analysis and offensive language identification share similar discourse properties. The selection of these tasks is motivated by the lack of large labelled data for user-generated code-mixed datasets. This paper works on code-mixed YouTube comments for Tamil, Malayalam, and Kannada languages. Our framework is applicable to other sequence classification problems irrespective of the size of the data"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2108.03867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CC","submitted_at":"2021-08-09T08:26:17Z","cross_cats_sorted":[],"title_canon_sha256":"d4d54e89729506647f4be3bda16896c140c1b45c7b2a9ddae0898f5f6654a3a3","abstract_canon_sha256":"ecd6bf0e5a144b067722864208e1a39fed267c6e2958d67dc9884a7855ab5947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:10.472448Z","signature_b64":"i9nRpzBHKUDEgfGwPMqa3nAQXLTL6tBTBmudLSH4CG4BUKTiIl6InlX6zYg/sAElH/1nzER6xbzZFsbKZTFGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2538676d15aff6f4fa2c3e3e764b057b2db466e6b8137ca222a46fca1b25b336","last_reissued_at":"2026-07-05T03:04:10.471994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:10.471994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Multi-Task Learning for Sentiment Analysis and Offensive Language Identification in Under-Resourced Dravidian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CC","authors_text":"Adeep Hande, Bharathi Raja Chakravarthi, Prasanna Kumar Kumaresan, Rahul Ponnusamy, Ruba Priyadharshini, Sajeetha Thavareesan, Siddhanth U Hegde","submitted_at":"2021-08-09T08:26:17Z","abstract_excerpt":"To obtain extensive annotated data for under-resourced languages is challenging, so in this research, we have investigated whether it is beneficial to train models using multi-task learning. Sentiment analysis and offensive language identification share similar discourse properties. The selection of these tasks is motivated by the lack of large labelled data for user-generated code-mixed datasets. This paper works on code-mixed YouTube comments for Tamil, Malayalam, and Kannada languages. Our framework is applicable to other sequence classification problems irrespective of the size of the data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03867","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.03867/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2108.03867","created_at":"2026-07-05T03:04:10.472054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.03867v1","created_at":"2026-07-05T03:04:10.472054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03867","created_at":"2026-07-05T03:04:10.472054+00:00"},{"alias_kind":"pith_short_12","alias_value":"EU4GO3IVV73P","created_at":"2026-07-05T03:04:10.472054+00:00"},{"alias_kind":"pith_short_16","alias_value":"EU4GO3IVV73PJ6RM","created_at":"2026-07-05T03:04:10.472054+00:00"},{"alias_kind":"pith_short_8","alias_value":"EU4GO3IV","created_at":"2026-07-05T03:04:10.472054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM","json":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM.json","graph_json":"https://pith.science/api/pith-number/EU4GO3IVV73PJ6RMHY7HMSYFPM/graph.json","events_json":"https://pith.science/api/pith-number/EU4GO3IVV73PJ6RMHY7HMSYFPM/events.json","paper":"https://pith.science/paper/EU4GO3IV"},"agent_actions":{"view_html":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM","download_json":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM.json","view_paper":"https://pith.science/paper/EU4GO3IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.03867&json=true","fetch_graph":"https://pith.science/api/pith-number/EU4GO3IVV73PJ6RMHY7HMSYFPM/graph.json","fetch_events":"https://pith.science/api/pith-number/EU4GO3IVV73PJ6RMHY7HMSYFPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM/action/storage_attestation","attest_author":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM/action/author_attestation","sign_citation":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM/action/citation_signature","submit_replication":"https://pith.science/pith/EU4GO3IVV73PJ6RMHY7HMSYFPM/action/replication_record"}},"created_at":"2026-07-05T03:04:10.472054+00:00","updated_at":"2026-07-05T03:04:10.472054+00:00"}