{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KXVMMX6JFPXPWZC5QEACPKN6JT","short_pith_number":"pith:KXVMMX6J","schema_version":"1.0","canonical_sha256":"55eac65fc92beefb645d810027a9be4cfcdeb1c13d48e2fcff5cd8f3ca51ef0b","source":{"kind":"arxiv","id":"1705.08488","version":1},"attestation_state":"computed","paper":{"title":"Second-Order Word Embeddings from Nearest Neighbor Topological Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Denis Newman-Griffis, Eric Fosler-Lussier","submitted_at":"2017-05-23T19:12:05Z","abstract_excerpt":"We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings. We then analyze the effects of using second-order embeddings as input features in two deep natural language processing models, for named entity recognition and recognizing textual entailment, as well as a linear model for paraphrase recognition. Surprisingly, we find that nearest neighbor information alone is sufficient to capture most of the performance benefits derived from using pre-trained word embeddings. Furthermore, second-order emb"},"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":"1705.08488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-23T19:12:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f09bb730b5cc8f1628c227557dab5b87755eb525e3cc3aae58c9b6fe985f212","abstract_canon_sha256":"19c31477deca1ee16e6dd30d95803a605f000bb99655088f096b9f5fe0c273ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:45.978512Z","signature_b64":"X+l1e64exsyVCtYmn58zUomsX9rhTV+nM7iTgaDergCkrouJym7orDRwfAtHmtgilEXf2RwkwPSwYZGY//1nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55eac65fc92beefb645d810027a9be4cfcdeb1c13d48e2fcff5cd8f3ca51ef0b","last_reissued_at":"2026-05-18T00:43:45.977891Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:45.977891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Second-Order Word Embeddings from Nearest Neighbor Topological Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Denis Newman-Griffis, Eric Fosler-Lussier","submitted_at":"2017-05-23T19:12:05Z","abstract_excerpt":"We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings. We then analyze the effects of using second-order embeddings as input features in two deep natural language processing models, for named entity recognition and recognizing textual entailment, as well as a linear model for paraphrase recognition. Surprisingly, we find that nearest neighbor information alone is sufficient to capture most of the performance benefits derived from using pre-trained word embeddings. Furthermore, second-order emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08488","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":"1705.08488","created_at":"2026-05-18T00:43:45.977985+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08488v1","created_at":"2026-05-18T00:43:45.977985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08488","created_at":"2026-05-18T00:43:45.977985+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXVMMX6JFPXP","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXVMMX6JFPXPWZC5","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXVMMX6J","created_at":"2026-05-18T12:31:28.150371+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/KXVMMX6JFPXPWZC5QEACPKN6JT","json":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT.json","graph_json":"https://pith.science/api/pith-number/KXVMMX6JFPXPWZC5QEACPKN6JT/graph.json","events_json":"https://pith.science/api/pith-number/KXVMMX6JFPXPWZC5QEACPKN6JT/events.json","paper":"https://pith.science/paper/KXVMMX6J"},"agent_actions":{"view_html":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT","download_json":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT.json","view_paper":"https://pith.science/paper/KXVMMX6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08488&json=true","fetch_graph":"https://pith.science/api/pith-number/KXVMMX6JFPXPWZC5QEACPKN6JT/graph.json","fetch_events":"https://pith.science/api/pith-number/KXVMMX6JFPXPWZC5QEACPKN6JT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/action/storage_attestation","attest_author":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/action/author_attestation","sign_citation":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/action/citation_signature","submit_replication":"https://pith.science/pith/KXVMMX6JFPXPWZC5QEACPKN6JT/action/replication_record"}},"created_at":"2026-05-18T00:43:45.977985+00:00","updated_at":"2026-05-18T00:43:45.977985+00:00"}