{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZDALF5RYFT5GP2G6NK7KZLHVQV","short_pith_number":"pith:ZDALF5RY","schema_version":"1.0","canonical_sha256":"c8c0b2f6382cfa67e8de6abeacacf5856b00cb710d9eb5770f97307ec2747961","source":{"kind":"arxiv","id":"1708.03994","version":1},"attestation_state":"computed","paper":{"title":"Data Sets: Word Embeddings Learned from Tweets and General Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.CL","authors_text":"Armineh Nourbakhsh, Quanzhi Li, Sameena Shah, Xiaomo Liu","submitted_at":"2017-08-14T02:34:17Z","abstract_excerpt":"A word embedding is a low-dimensional, dense and real- valued vector representation of a word. Word embeddings have been used in many NLP tasks. They are usually gener- ated from a large text corpus. The embedding of a word cap- tures both its syntactic and semantic aspects. Tweets are short, noisy and have unique lexical and semantic features that are different from other types of text. Therefore, it is necessary to have word embeddings learned specifically from tweets. In this paper, we present ten word embedding data sets. In addition to the data sets learned from just tweet data, we also b"},"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":"1708.03994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-14T02:34:17Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"91309a27ee373842b89100ffcf3bfa8d5474520f76195c5c3ccb336d27ac7520","abstract_canon_sha256":"48c06f23fc285eef2213cef13c3720db291609c59e791098964f1a4f52aec106"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:07.328901Z","signature_b64":"GLEGcP9LwTHV1ZZTp8c15tmS7LeqIAByA7cjRuUlMlMsdYOeMty4KoHiGJ/OJEXX73all3TVmfgfzFywRKmAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c0b2f6382cfa67e8de6abeacacf5856b00cb710d9eb5770f97307ec2747961","last_reissued_at":"2026-05-18T00:38:07.328426Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:07.328426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Sets: Word Embeddings Learned from Tweets and General Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.CL","authors_text":"Armineh Nourbakhsh, Quanzhi Li, Sameena Shah, Xiaomo Liu","submitted_at":"2017-08-14T02:34:17Z","abstract_excerpt":"A word embedding is a low-dimensional, dense and real- valued vector representation of a word. Word embeddings have been used in many NLP tasks. They are usually gener- ated from a large text corpus. The embedding of a word cap- tures both its syntactic and semantic aspects. Tweets are short, noisy and have unique lexical and semantic features that are different from other types of text. Therefore, it is necessary to have word embeddings learned specifically from tweets. In this paper, we present ten word embedding data sets. In addition to the data sets learned from just tweet data, we also b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03994","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":"1708.03994","created_at":"2026-05-18T00:38:07.328494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.03994v1","created_at":"2026-05-18T00:38:07.328494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03994","created_at":"2026-05-18T00:38:07.328494+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDALF5RYFT5G","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDALF5RYFT5GP2G6","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDALF5RY","created_at":"2026-05-18T12:31:59.375834+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/ZDALF5RYFT5GP2G6NK7KZLHVQV","json":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV.json","graph_json":"https://pith.science/api/pith-number/ZDALF5RYFT5GP2G6NK7KZLHVQV/graph.json","events_json":"https://pith.science/api/pith-number/ZDALF5RYFT5GP2G6NK7KZLHVQV/events.json","paper":"https://pith.science/paper/ZDALF5RY"},"agent_actions":{"view_html":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV","download_json":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV.json","view_paper":"https://pith.science/paper/ZDALF5RY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.03994&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDALF5RYFT5GP2G6NK7KZLHVQV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDALF5RYFT5GP2G6NK7KZLHVQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV/action/storage_attestation","attest_author":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV/action/author_attestation","sign_citation":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV/action/citation_signature","submit_replication":"https://pith.science/pith/ZDALF5RYFT5GP2G6NK7KZLHVQV/action/replication_record"}},"created_at":"2026-05-18T00:38:07.328494+00:00","updated_at":"2026-05-18T00:38:07.328494+00:00"}