{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QWFOZV4PCU5NV4K43X2MUMWUXQ","short_pith_number":"pith:QWFOZV4P","schema_version":"1.0","canonical_sha256":"858aecd78f153adaf15cddf4ca32d4bc1fc41944e0c94fd12f5e7828041779c0","source":{"kind":"arxiv","id":"1510.02387","version":2},"attestation_state":"computed","paper":{"title":"Mapping Unseen Words to Task-Trained Embedding Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Karen Livescu, Kevin Gimpel, Mohit Bansal, Pranava Swaroop Madhyastha","submitted_at":"2015-10-08T16:17:47Z","abstract_excerpt":"We consider the supervised training setting in which we learn task-specific word embeddings. We assume that we start with initial embeddings learned from unlabelled data and update them to learn task-specific embeddings for words in the supervised training data. However, for new words in the test set, we must use either their initial embeddings or a single unknown embedding, which often leads to errors. We address this by learning a neural network to map from initial embeddings to the task-specific embedding space, via a multi-loss objective function. The technique is general, but here we demo"},"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":"1510.02387","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-10-08T16:17:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99de2633740a6df3ff05292bbe936f0a03c100a8c24488bf6bf7de31d2adf62b","abstract_canon_sha256":"a764864d9d230b403dbc7fcc3481a9533f2598e04a0f622b323e5f991dce862f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:00.323931Z","signature_b64":"XufebyS64VPQM/tu5a+lhP9fNeyBEUNFTDwedHob11G27ake+119xKk4P3PpyUHe1rVAGiwsrZXZPApO2sBBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"858aecd78f153adaf15cddf4ca32d4bc1fc41944e0c94fd12f5e7828041779c0","last_reissued_at":"2026-05-18T01:12:00.323599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:00.323599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping Unseen Words to Task-Trained Embedding Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Karen Livescu, Kevin Gimpel, Mohit Bansal, Pranava Swaroop Madhyastha","submitted_at":"2015-10-08T16:17:47Z","abstract_excerpt":"We consider the supervised training setting in which we learn task-specific word embeddings. We assume that we start with initial embeddings learned from unlabelled data and update them to learn task-specific embeddings for words in the supervised training data. However, for new words in the test set, we must use either their initial embeddings or a single unknown embedding, which often leads to errors. We address this by learning a neural network to map from initial embeddings to the task-specific embedding space, via a multi-loss objective function. The technique is general, but here we demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.02387","kind":"arxiv","version":2},"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":"1510.02387","created_at":"2026-05-18T01:12:00.323655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.02387v2","created_at":"2026-05-18T01:12:00.323655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.02387","created_at":"2026-05-18T01:12:00.323655+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWFOZV4PCU5N","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWFOZV4PCU5NV4K4","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWFOZV4P","created_at":"2026-05-18T12:29:39.896362+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/QWFOZV4PCU5NV4K43X2MUMWUXQ","json":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ.json","graph_json":"https://pith.science/api/pith-number/QWFOZV4PCU5NV4K43X2MUMWUXQ/graph.json","events_json":"https://pith.science/api/pith-number/QWFOZV4PCU5NV4K43X2MUMWUXQ/events.json","paper":"https://pith.science/paper/QWFOZV4P"},"agent_actions":{"view_html":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ","download_json":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ.json","view_paper":"https://pith.science/paper/QWFOZV4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.02387&json=true","fetch_graph":"https://pith.science/api/pith-number/QWFOZV4PCU5NV4K43X2MUMWUXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QWFOZV4PCU5NV4K43X2MUMWUXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ/action/storage_attestation","attest_author":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ/action/author_attestation","sign_citation":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ/action/citation_signature","submit_replication":"https://pith.science/pith/QWFOZV4PCU5NV4K43X2MUMWUXQ/action/replication_record"}},"created_at":"2026-05-18T01:12:00.323655+00:00","updated_at":"2026-05-18T01:12:00.323655+00:00"}