{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:47YQJZSXAZPMKVEUS7ZYNZDVBD","short_pith_number":"pith:47YQJZSX","schema_version":"1.0","canonical_sha256":"e7f104e657065ec5549497f386e47508dc0b84dd1d13d1ec8c8f5accf80e5052","source":{"kind":"arxiv","id":"1401.2937","version":1},"attestation_state":"computed","paper":{"title":"A survey of methods to ease the development of highly multilingual text mining applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ralf Steinberger","submitted_at":"2014-01-13T18:05:28Z","abstract_excerpt":"Multilingual text processing is useful because the information content found in different languages is complementary, both regarding facts and opinions. While Information Extraction and other text mining software can, in principle, be developed for many languages, most text analysis tools have only been applied to small sets of languages because the development effort per language is large. Self-training tools obviously alleviate the problem, but even the effort of providing training data and of manually tuning the results is usually considerable. In this paper, we gather insights by various m"},"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":"1401.2937","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-13T18:05:28Z","cross_cats_sorted":[],"title_canon_sha256":"a41d6bb8b5536262e009f3299596e0786552d83d232c67d78202bc47eeca3546","abstract_canon_sha256":"354bf71f1a50e359efdf5d296aeffd36b0fc8515886d50a08bf9acb6940df58d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:02:31.490086Z","signature_b64":"av28/jZTHyCID+PA3OQtJAvDXSJPb+1ie7pC21R66/eqYbREo7Hu7+5oqGQCektqv31IWd1MlkYR4dxEKBEoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f104e657065ec5549497f386e47508dc0b84dd1d13d1ec8c8f5accf80e5052","last_reissued_at":"2026-05-18T03:02:31.489371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:02:31.489371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A survey of methods to ease the development of highly multilingual text mining applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ralf Steinberger","submitted_at":"2014-01-13T18:05:28Z","abstract_excerpt":"Multilingual text processing is useful because the information content found in different languages is complementary, both regarding facts and opinions. While Information Extraction and other text mining software can, in principle, be developed for many languages, most text analysis tools have only been applied to small sets of languages because the development effort per language is large. Self-training tools obviously alleviate the problem, but even the effort of providing training data and of manually tuning the results is usually considerable. In this paper, we gather insights by various m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.2937","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":"1401.2937","created_at":"2026-05-18T03:02:31.489497+00:00"},{"alias_kind":"arxiv_version","alias_value":"1401.2937v1","created_at":"2026-05-18T03:02:31.489497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.2937","created_at":"2026-05-18T03:02:31.489497+00:00"},{"alias_kind":"pith_short_12","alias_value":"47YQJZSXAZPM","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_16","alias_value":"47YQJZSXAZPMKVEU","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_8","alias_value":"47YQJZSX","created_at":"2026-05-18T12:28:14.216126+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/47YQJZSXAZPMKVEUS7ZYNZDVBD","json":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD.json","graph_json":"https://pith.science/api/pith-number/47YQJZSXAZPMKVEUS7ZYNZDVBD/graph.json","events_json":"https://pith.science/api/pith-number/47YQJZSXAZPMKVEUS7ZYNZDVBD/events.json","paper":"https://pith.science/paper/47YQJZSX"},"agent_actions":{"view_html":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD","download_json":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD.json","view_paper":"https://pith.science/paper/47YQJZSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1401.2937&json=true","fetch_graph":"https://pith.science/api/pith-number/47YQJZSXAZPMKVEUS7ZYNZDVBD/graph.json","fetch_events":"https://pith.science/api/pith-number/47YQJZSXAZPMKVEUS7ZYNZDVBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD/action/storage_attestation","attest_author":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD/action/author_attestation","sign_citation":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD/action/citation_signature","submit_replication":"https://pith.science/pith/47YQJZSXAZPMKVEUS7ZYNZDVBD/action/replication_record"}},"created_at":"2026-05-18T03:02:31.489497+00:00","updated_at":"2026-05-18T03:02:31.489497+00:00"}