{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WEIUXTM7LI3GC2WWUA2LSCMNQU","short_pith_number":"pith:WEIUXTM7","schema_version":"1.0","canonical_sha256":"b1114bcd9f5a36616ad6a034b9098d851268b5ef7c5cf0421c48537a58d13a8c","source":{"kind":"arxiv","id":"1812.11760","version":2},"attestation_state":"computed","paper":{"title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Klein, Nikita Kitaev, Steven Cao","submitted_at":"2018-12-31T11:01:02Z","abstract_excerpt":"We show that constituency parsing benefits from unsupervised pre-training across a variety of languages and a range of pre-training conditions. We first compare the benefits of no pre-training, fastText, ELMo, and BERT for English and find that BERT outperforms ELMo, in large part due to increased model capacity, whereas ELMo in turn outperforms the non-contextual fastText embeddings. We also find that pre-training is beneficial across all 11 languages tested; however, large model sizes (more than 100 million parameters) make it computationally expensive to train separate models for each langu"},"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":"1812.11760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-31T11:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"4ec5f73c72cdb1faa6879a10109c06d7e53601c2dab62ff1b91266e8e0192d72","abstract_canon_sha256":"c47d508226a9f4c0a9e9803b6d762be8ac5610ee9234a068b1f4b1d2211f878b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:21.891635Z","signature_b64":"Dz+bxarjofTnwtF7t+Vx+McPYL6tlMulXKQSGsDK1mJzmWoiN4mWQRuePI/LySJTfcUT48pN4AogVV7qGBJCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1114bcd9f5a36616ad6a034b9098d851268b5ef7c5cf0421c48537a58d13a8c","last_reissued_at":"2026-05-17T23:44:21.890949Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:21.890949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Klein, Nikita Kitaev, Steven Cao","submitted_at":"2018-12-31T11:01:02Z","abstract_excerpt":"We show that constituency parsing benefits from unsupervised pre-training across a variety of languages and a range of pre-training conditions. We first compare the benefits of no pre-training, fastText, ELMo, and BERT for English and find that BERT outperforms ELMo, in large part due to increased model capacity, whereas ELMo in turn outperforms the non-contextual fastText embeddings. We also find that pre-training is beneficial across all 11 languages tested; however, large model sizes (more than 100 million parameters) make it computationally expensive to train separate models for each langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11760","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":"1812.11760","created_at":"2026-05-17T23:44:21.891051+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11760v2","created_at":"2026-05-17T23:44:21.891051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11760","created_at":"2026-05-17T23:44:21.891051+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEIUXTM7LI3G","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEIUXTM7LI3GC2WW","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEIUXTM7","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2404.12377","citing_title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU","json":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU.json","graph_json":"https://pith.science/api/pith-number/WEIUXTM7LI3GC2WWUA2LSCMNQU/graph.json","events_json":"https://pith.science/api/pith-number/WEIUXTM7LI3GC2WWUA2LSCMNQU/events.json","paper":"https://pith.science/paper/WEIUXTM7"},"agent_actions":{"view_html":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU","download_json":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU.json","view_paper":"https://pith.science/paper/WEIUXTM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11760&json=true","fetch_graph":"https://pith.science/api/pith-number/WEIUXTM7LI3GC2WWUA2LSCMNQU/graph.json","fetch_events":"https://pith.science/api/pith-number/WEIUXTM7LI3GC2WWUA2LSCMNQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU/action/storage_attestation","attest_author":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU/action/author_attestation","sign_citation":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU/action/citation_signature","submit_replication":"https://pith.science/pith/WEIUXTM7LI3GC2WWUA2LSCMNQU/action/replication_record"}},"created_at":"2026-05-17T23:44:21.891051+00:00","updated_at":"2026-05-17T23:44:21.891051+00:00"}