{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZOBFK5UVZFF4RCOW3TRAXVXLAM","short_pith_number":"pith:ZOBFK5UV","schema_version":"1.0","canonical_sha256":"cb82557695c94bc889d6dce20bd6eb0300edf93a241207ea312663f148e67000","source":{"kind":"arxiv","id":"1804.08756","version":1},"attestation_state":"computed","paper":{"title":"Detecting Syntactic Features of Translated Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Hu, Sandra K\\\"ubler, Wen Li","submitted_at":"2018-04-23T21:56:11Z","abstract_excerpt":"We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we "},"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":"1804.08756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T21:56:11Z","cross_cats_sorted":[],"title_canon_sha256":"d88ad948dbc3c6e0bd8b79da8e41767dafc58d6d97a1e71db4710a46e5419cda","abstract_canon_sha256":"3837b607733a8fe6093fd3b53c09e5d027b616e344c247b8cf812a7a9ebb2b98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:37.445052Z","signature_b64":"pJkOBvpiXNbxEspU/zhY6OD2/77LqEiELeUahs9hoq8ZJT6otGMYRynzcihzMKweA8OK03bMd5d3nKFKiosfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb82557695c94bc889d6dce20bd6eb0300edf93a241207ea312663f148e67000","last_reissued_at":"2026-05-18T00:17:37.444208Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:37.444208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Syntactic Features of Translated Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Hu, Sandra K\\\"ubler, Wen Li","submitted_at":"2018-04-23T21:56:11Z","abstract_excerpt":"We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08756","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":"1804.08756","created_at":"2026-05-18T00:17:37.444343+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08756v1","created_at":"2026-05-18T00:17:37.444343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08756","created_at":"2026-05-18T00:17:37.444343+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOBFK5UVZFF4","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOBFK5UVZFF4RCOW","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOBFK5UV","created_at":"2026-05-18T12:33:07.085635+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/ZOBFK5UVZFF4RCOW3TRAXVXLAM","json":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM.json","graph_json":"https://pith.science/api/pith-number/ZOBFK5UVZFF4RCOW3TRAXVXLAM/graph.json","events_json":"https://pith.science/api/pith-number/ZOBFK5UVZFF4RCOW3TRAXVXLAM/events.json","paper":"https://pith.science/paper/ZOBFK5UV"},"agent_actions":{"view_html":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM","download_json":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM.json","view_paper":"https://pith.science/paper/ZOBFK5UV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08756&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOBFK5UVZFF4RCOW3TRAXVXLAM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOBFK5UVZFF4RCOW3TRAXVXLAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/action/storage_attestation","attest_author":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/action/author_attestation","sign_citation":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/action/citation_signature","submit_replication":"https://pith.science/pith/ZOBFK5UVZFF4RCOW3TRAXVXLAM/action/replication_record"}},"created_at":"2026-05-18T00:17:37.444343+00:00","updated_at":"2026-05-18T00:17:37.444343+00:00"}