{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZXCR6UUTAG5W2K3U3VB6V5DCUG","short_pith_number":"pith:ZXCR6UUT","schema_version":"1.0","canonical_sha256":"cdc51f529301bb6d2b74dd43eaf462a1a4333c583e9a3ed88f32d1a0c21d5efc","source":{"kind":"arxiv","id":"1910.00163","version":1},"attestation_state":"computed","paper":{"title":"Specializing Word Embeddings (for Parsing) by Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jason Eisner, Xiang Lisa Li","submitted_at":"2019-10-01T00:47:31Z","abstract_excerpt":"Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks. We propose a very fast variational information bottleneck (VIB) method to nonlinearly compress these embeddings, keeping only the information that helps a discriminative parser. We compress each word embedding to either a discrete tag or a continuous vector. In the discrete version, our automatically compressed tags form an alternative tag set: we show experimentally that our tags capture most of the information in traditional POS tag annot"},"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":"1910.00163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-01T00:47:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e39dba55bf22bd86a856c6e84313c87d47f32316b633f621ba5c06219457196a","abstract_canon_sha256":"319209d5a5b726269d4e97255443d97879cf13db9944b16b201769748ec36492"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:43.049703Z","signature_b64":"KMzcEfLbovxuqNq7cEgY7lewFzxzEKDtfUcbYMEP/LXq4kN56dKmcvOIaHbZ016bnXmOoFYq7apbHdP994XsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc51f529301bb6d2b74dd43eaf462a1a4333c583e9a3ed88f32d1a0c21d5efc","last_reissued_at":"2026-07-05T00:08:43.049368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:43.049368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Specializing Word Embeddings (for Parsing) by Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jason Eisner, Xiang Lisa Li","submitted_at":"2019-10-01T00:47:31Z","abstract_excerpt":"Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks. We propose a very fast variational information bottleneck (VIB) method to nonlinearly compress these embeddings, keeping only the information that helps a discriminative parser. We compress each word embedding to either a discrete tag or a continuous vector. In the discrete version, our automatically compressed tags form an alternative tag set: we show experimentally that our tags capture most of the information in traditional POS tag annot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00163","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.00163/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1910.00163","created_at":"2026-07-05T00:08:43.049423+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.00163v1","created_at":"2026-07-05T00:08:43.049423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00163","created_at":"2026-07-05T00:08:43.049423+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXCR6UUTAG5W","created_at":"2026-07-05T00:08:43.049423+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXCR6UUTAG5W2K3U","created_at":"2026-07-05T00:08:43.049423+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXCR6UUT","created_at":"2026-07-05T00:08:43.049423+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/ZXCR6UUTAG5W2K3U3VB6V5DCUG","json":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG.json","graph_json":"https://pith.science/api/pith-number/ZXCR6UUTAG5W2K3U3VB6V5DCUG/graph.json","events_json":"https://pith.science/api/pith-number/ZXCR6UUTAG5W2K3U3VB6V5DCUG/events.json","paper":"https://pith.science/paper/ZXCR6UUT"},"agent_actions":{"view_html":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG","download_json":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG.json","view_paper":"https://pith.science/paper/ZXCR6UUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.00163&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXCR6UUTAG5W2K3U3VB6V5DCUG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXCR6UUTAG5W2K3U3VB6V5DCUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG/action/storage_attestation","attest_author":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG/action/author_attestation","sign_citation":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG/action/citation_signature","submit_replication":"https://pith.science/pith/ZXCR6UUTAG5W2K3U3VB6V5DCUG/action/replication_record"}},"created_at":"2026-07-05T00:08:43.049423+00:00","updated_at":"2026-07-05T00:08:43.049423+00:00"}