{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WTUDJ2PXB2IQXRB53ZHZNJQTPL","short_pith_number":"pith:WTUDJ2PX","schema_version":"1.0","canonical_sha256":"b4e834e9f70e910bc43dde4f96a6137aff529ad7058551aed6f8fa34bced013c","source":{"kind":"arxiv","id":"2101.03289","version":5},"attestation_state":"computed","paper":{"title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Pouran Ben Veyseh, Minh Van Nguyen, Thien Huu Nguyen, Viet Dac Lai","submitted_at":"2021-01-09T04:55:52Z","abstract_excerpt":"We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependen"},"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":"2101.03289","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-09T04:55:52Z","cross_cats_sorted":[],"title_canon_sha256":"c000a51448bf185d444df6105ea8cc74afe33d4f7662905dbd39cbce0c2d18b5","abstract_canon_sha256":"545ad01239942703ba239b16335aaa0c2f20e14b2ffb6ea5e187114acf0b2c18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:45.107088Z","signature_b64":"UcrC0BkK0v9ln21PibhuhVBYbgDNuQztCc0Kl1vZP5eE53aAFXldb8Kse9lzN5BwsrL3BOo5NxylEhmVagiuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e834e9f70e910bc43dde4f96a6137aff529ad7058551aed6f8fa34bced013c","last_reissued_at":"2026-07-05T03:22:45.106690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:45.106690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Pouran Ben Veyseh, Minh Van Nguyen, Thien Huu Nguyen, Viet Dac Lai","submitted_at":"2021-01-09T04:55:52Z","abstract_excerpt":"We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03289","kind":"arxiv","version":5},"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/2101.03289/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":"2101.03289","created_at":"2026-07-05T03:22:45.106750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.03289v5","created_at":"2026-07-05T03:22:45.106750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03289","created_at":"2026-07-05T03:22:45.106750+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTUDJ2PXB2IQ","created_at":"2026-07-05T03:22:45.106750+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTUDJ2PXB2IQXRB5","created_at":"2026-07-05T03:22:45.106750+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTUDJ2PX","created_at":"2026-07-05T03:22:45.106750+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/WTUDJ2PXB2IQXRB53ZHZNJQTPL","json":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL.json","graph_json":"https://pith.science/api/pith-number/WTUDJ2PXB2IQXRB53ZHZNJQTPL/graph.json","events_json":"https://pith.science/api/pith-number/WTUDJ2PXB2IQXRB53ZHZNJQTPL/events.json","paper":"https://pith.science/paper/WTUDJ2PX"},"agent_actions":{"view_html":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL","download_json":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL.json","view_paper":"https://pith.science/paper/WTUDJ2PX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.03289&json=true","fetch_graph":"https://pith.science/api/pith-number/WTUDJ2PXB2IQXRB53ZHZNJQTPL/graph.json","fetch_events":"https://pith.science/api/pith-number/WTUDJ2PXB2IQXRB53ZHZNJQTPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL/action/storage_attestation","attest_author":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL/action/author_attestation","sign_citation":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL/action/citation_signature","submit_replication":"https://pith.science/pith/WTUDJ2PXB2IQXRB53ZHZNJQTPL/action/replication_record"}},"created_at":"2026-07-05T03:22:45.106750+00:00","updated_at":"2026-07-05T03:22:45.106750+00:00"}