{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BCYFYYLIQEFXUIXT4HE6RTFNYZ","short_pith_number":"pith:BCYFYYLI","schema_version":"1.0","canonical_sha256":"08b05c6168810b7a22f3e1c9e8ccadc67a70bb312e696182a45a8b7292173c43","source":{"kind":"arxiv","id":"1908.01294","version":2},"attestation_state":"computed","paper":{"title":"Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanatip Saetia, Ekapol Chuangsuwanich, Peerapon Vateekul, Tawunrat Chalothorn","submitted_at":"2019-08-04T08:24:05Z","abstract_excerpt":"A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep learning model for the task of sentence segmentation that includes three main contributions. First, we integrate n-gram embedding as a local representation to capture word groups near sentence boundaries. Second, to focus on the keywords of dependent clauses, we combine the model with a distant representation obtained from self-attention modules. Finally, due to the scarcity of la"},"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":"1908.01294","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-04T08:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"6f680eb9f61db5c6bf9c0f5f0a16ce5fd4f47661e993cc09cc5185b40e158cad","abstract_canon_sha256":"4db4fec1c518f02d6dcea01fb7b45092229c808388287d552a6073e565eca550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:34.313808Z","signature_b64":"7RUWNnzVLQl+hTboqDK1NjF+JvS56f2LJ00EZicXL/WHVWR4+EvEOtLN3CtrtngCFJcBv9lpCBnhKmryBYNyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b05c6168810b7a22f3e1c9e8ccadc67a70bb312e696182a45a8b7292173c43","last_reissued_at":"2026-07-04T23:59:34.313435Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:34.313435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanatip Saetia, Ekapol Chuangsuwanich, Peerapon Vateekul, Tawunrat Chalothorn","submitted_at":"2019-08-04T08:24:05Z","abstract_excerpt":"A sentence is typically treated as the minimal syntactic unit used for extracting valuable information from a longer piece of text. However, in written Thai, there are no explicit sentence markers. We proposed a deep learning model for the task of sentence segmentation that includes three main contributions. First, we integrate n-gram embedding as a local representation to capture word groups near sentence boundaries. Second, to focus on the keywords of dependent clauses, we combine the model with a distant representation obtained from self-attention modules. Finally, due to the scarcity of la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01294","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.01294/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":"1908.01294","created_at":"2026-07-04T23:59:34.313499+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01294v2","created_at":"2026-07-04T23:59:34.313499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01294","created_at":"2026-07-04T23:59:34.313499+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCYFYYLIQEFX","created_at":"2026-07-04T23:59:34.313499+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCYFYYLIQEFXUIXT","created_at":"2026-07-04T23:59:34.313499+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCYFYYLI","created_at":"2026-07-04T23:59:34.313499+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/BCYFYYLIQEFXUIXT4HE6RTFNYZ","json":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ.json","graph_json":"https://pith.science/api/pith-number/BCYFYYLIQEFXUIXT4HE6RTFNYZ/graph.json","events_json":"https://pith.science/api/pith-number/BCYFYYLIQEFXUIXT4HE6RTFNYZ/events.json","paper":"https://pith.science/paper/BCYFYYLI"},"agent_actions":{"view_html":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ","download_json":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ.json","view_paper":"https://pith.science/paper/BCYFYYLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01294&json=true","fetch_graph":"https://pith.science/api/pith-number/BCYFYYLIQEFXUIXT4HE6RTFNYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BCYFYYLIQEFXUIXT4HE6RTFNYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/action/storage_attestation","attest_author":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/action/author_attestation","sign_citation":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/action/citation_signature","submit_replication":"https://pith.science/pith/BCYFYYLIQEFXUIXT4HE6RTFNYZ/action/replication_record"}},"created_at":"2026-07-04T23:59:34.313499+00:00","updated_at":"2026-07-04T23:59:34.313499+00:00"}