{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:MOHBV43URCK73WJB6Q4VE3RCQP","short_pith_number":"pith:MOHBV43U","schema_version":"1.0","canonical_sha256":"638e1af3748895fdd921f439526e2283e619f0376ece60a43f754d4673ab2f0d","source":{"kind":"arxiv","id":"1405.4273","version":1},"attestation_state":"computed","paper":{"title":"Compositional Morphology for Word Representations and Language Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jan A. Botha, Phil Blunsom","submitted_at":"2014-05-16T19:08:14Z","abstract_excerpt":"This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. W"},"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":"1405.4273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-05-16T19:08:14Z","cross_cats_sorted":[],"title_canon_sha256":"788d3c0628abb71702896758953b66c0b4561acd9c171cdc3c6f99c49a7d1b91","abstract_canon_sha256":"8ae2c591b9d9c7be12c543eac7b97c2a20846b319b1d9b142c4874f13263e277"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:51:42.794303Z","signature_b64":"lP60o2l16s7fZReDMjlrN5mq00rVdaTitSrwXd2aC+kTPSYO2sdCT5epsGsTMyShAPix++DMZPa1zllPLCG/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"638e1af3748895fdd921f439526e2283e619f0376ece60a43f754d4673ab2f0d","last_reissued_at":"2026-05-18T02:51:42.793809Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:51:42.793809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Morphology for Word Representations and Language Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jan A. Botha, Phil Blunsom","submitted_at":"2014-05-16T19:08:14Z","abstract_excerpt":"This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.4273","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":""},"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":"1405.4273","created_at":"2026-05-18T02:51:42.793889+00:00"},{"alias_kind":"arxiv_version","alias_value":"1405.4273v1","created_at":"2026-05-18T02:51:42.793889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.4273","created_at":"2026-05-18T02:51:42.793889+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOHBV43URCK7","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOHBV43URCK73WJB","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOHBV43U","created_at":"2026-05-18T12:28:38.356838+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/MOHBV43URCK73WJB6Q4VE3RCQP","json":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP.json","graph_json":"https://pith.science/api/pith-number/MOHBV43URCK73WJB6Q4VE3RCQP/graph.json","events_json":"https://pith.science/api/pith-number/MOHBV43URCK73WJB6Q4VE3RCQP/events.json","paper":"https://pith.science/paper/MOHBV43U"},"agent_actions":{"view_html":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP","download_json":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP.json","view_paper":"https://pith.science/paper/MOHBV43U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1405.4273&json=true","fetch_graph":"https://pith.science/api/pith-number/MOHBV43URCK73WJB6Q4VE3RCQP/graph.json","fetch_events":"https://pith.science/api/pith-number/MOHBV43URCK73WJB6Q4VE3RCQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP/action/storage_attestation","attest_author":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP/action/author_attestation","sign_citation":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP/action/citation_signature","submit_replication":"https://pith.science/pith/MOHBV43URCK73WJB6Q4VE3RCQP/action/replication_record"}},"created_at":"2026-05-18T02:51:42.793889+00:00","updated_at":"2026-05-18T02:51:42.793889+00:00"}