{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EGTDUCCXCYX5L4V6CYG5XILATE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3e877ea75c7659b80df1f153c557a86912b618ed978929704a0b5a91411fe42d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-20T15:02:14Z","title_canon_sha256":"94e9e844b2259aee33d92e5e0aab3e996a713853de4e7acd6f9d7d380d93e12b"},"schema_version":"1.0","source":{"id":"1707.06556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06556","created_at":"2026-05-18T00:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06556v1","created_at":"2026-05-18T00:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06556","created_at":"2026-05-18T00:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"EGTDUCCXCYX5","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EGTDUCCXCYX5L4V6","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EGTDUCCX","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:97d5d182233174e5de52e5ad45161a0e7f236c3f4f0c108fcdaa8cf99300e091","target":"graph","created_at":"2026-05-18T00:39:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn 'a good vector' for a word, a model must have sufficient examples of its usage. This contradicts the fact that humans can guess the meaning of a word from a few occurrences only. In this paper, we show that a neural language model such as Word2Vec only necessitates minor modifications to its standard architecture to learn new terms from tiny data, using background knowledge from a previously learnt semantic space. We test our model on word definitions and on a nonce task invol","authors_text":"Aurelie Herbelot, Marco Baroni","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-20T15:02:14Z","title":"High-risk learning: acquiring new word vectors from tiny data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06556","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:08ace37270ef76d4473b29a080a2f5b3c571baa44696bd610f96ed7b66429e41","target":"record","created_at":"2026-05-18T00:39:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3e877ea75c7659b80df1f153c557a86912b618ed978929704a0b5a91411fe42d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-20T15:02:14Z","title_canon_sha256":"94e9e844b2259aee33d92e5e0aab3e996a713853de4e7acd6f9d7d380d93e12b"},"schema_version":"1.0","source":{"id":"1707.06556","kind":"arxiv","version":1}},"canonical_sha256":"21a63a0857162fd5f2be160ddba160993901364fecc5e76588d529539d4bf25b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21a63a0857162fd5f2be160ddba160993901364fecc5e76588d529539d4bf25b","first_computed_at":"2026-05-18T00:39:53.535313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:53.535313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kB7NGMndmgclf/6VNxK+rrBg/qJZIrKU6oNplJ16VAZRqwJyfBndhchv4PWfcQ329Ltx56P6sbDgaPp6ENy4Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:53.535983Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08ace37270ef76d4473b29a080a2f5b3c571baa44696bd610f96ed7b66429e41","sha256:97d5d182233174e5de52e5ad45161a0e7f236c3f4f0c108fcdaa8cf99300e091"],"state_sha256":"73812353e0297cb3b7b5dddb129b1b45480c98582d57396b30cac633d04b1560"}