{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WL3YVVGESCFDP4WRDCKFGMOTHL","short_pith_number":"pith:WL3YVVGE","schema_version":"1.0","canonical_sha256":"b2f78ad4c4908a37f2d118945331d33af80919aab9846ab9fcb1947964d292d5","source":{"kind":"arxiv","id":"1804.07849","version":4},"attestation_state":"computed","paper":{"title":"Mutual Information Maximization for Simple and Accurate Part-Of-Speech Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karl Stratos","submitted_at":"2018-04-20T22:34:29Z","abstract_excerpt":"We address part-of-speech (POS) induction by maximizing the mutual information between the induced label and its context. We focus on two training objectives that are amenable to stochastic gradient descent (SGD): a novel generalization of the classical Brown clustering objective and a recently proposed variational lower bound. While both objectives are subject to noise in gradient updates, we show through analysis and experiments that the variational lower bound is robust whereas the generalized Brown objective is vulnerable. We obtain competitive performance on a multitude of datasets and la"},"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":"1804.07849","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T22:34:29Z","cross_cats_sorted":[],"title_canon_sha256":"5528ccc41f8ed3a42fde1059b55a1796880cf5a9243a78a198b6af5023ac6ce1","abstract_canon_sha256":"c2da2e4aba89c1c61543fcaf5e9023f6d14ec2de2f13d65bda8a49e73b629617"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:33.619075Z","signature_b64":"yaWMGiFEiXnENxWjoO9Hb7i9xMNHxxDNbfl/i1+Iqjtc5cF7JHStgOQ1u9rMj6C5qyHwdT39AZJTq3zwRYBOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f78ad4c4908a37f2d118945331d33af80919aab9846ab9fcb1947964d292d5","last_reissued_at":"2026-05-17T23:49:33.618635Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:33.618635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mutual Information Maximization for Simple and Accurate Part-Of-Speech Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karl Stratos","submitted_at":"2018-04-20T22:34:29Z","abstract_excerpt":"We address part-of-speech (POS) induction by maximizing the mutual information between the induced label and its context. We focus on two training objectives that are amenable to stochastic gradient descent (SGD): a novel generalization of the classical Brown clustering objective and a recently proposed variational lower bound. While both objectives are subject to noise in gradient updates, we show through analysis and experiments that the variational lower bound is robust whereas the generalized Brown objective is vulnerable. We obtain competitive performance on a multitude of datasets and la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07849","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1804.07849","created_at":"2026-05-17T23:49:33.618697+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07849v4","created_at":"2026-05-17T23:49:33.618697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07849","created_at":"2026-05-17T23:49:33.618697+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL3YVVGESCFD","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL3YVVGESCFDP4WR","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL3YVVGE","created_at":"2026-05-18T12:33:01.666342+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/WL3YVVGESCFDP4WRDCKFGMOTHL","json":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL.json","graph_json":"https://pith.science/api/pith-number/WL3YVVGESCFDP4WRDCKFGMOTHL/graph.json","events_json":"https://pith.science/api/pith-number/WL3YVVGESCFDP4WRDCKFGMOTHL/events.json","paper":"https://pith.science/paper/WL3YVVGE"},"agent_actions":{"view_html":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL","download_json":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL.json","view_paper":"https://pith.science/paper/WL3YVVGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07849&json=true","fetch_graph":"https://pith.science/api/pith-number/WL3YVVGESCFDP4WRDCKFGMOTHL/graph.json","fetch_events":"https://pith.science/api/pith-number/WL3YVVGESCFDP4WRDCKFGMOTHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL/action/storage_attestation","attest_author":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL/action/author_attestation","sign_citation":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL/action/citation_signature","submit_replication":"https://pith.science/pith/WL3YVVGESCFDP4WRDCKFGMOTHL/action/replication_record"}},"created_at":"2026-05-17T23:49:33.618697+00:00","updated_at":"2026-05-17T23:49:33.618697+00:00"}