{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PSRHH7AJIZBWJRXRWOGIW5IVHN","short_pith_number":"pith:PSRHH7AJ","schema_version":"1.0","canonical_sha256":"7ca273fc09464364c6f1b38c8b75153b5224d8f9349b2a15173687b6cf4fe7b2","source":{"kind":"arxiv","id":"1709.00616","version":1},"attestation_state":"computed","paper":{"title":"Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Abdelali, Fahim Dalvi, Hassan Sajjad, Nadir Durrani, Stephan Vogel, Yonatan Belinkov","submitted_at":"2017-09-02T18:45:48Z","abstract_excerpt":"Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-independent alternatives to morphological segmentation using: i) data-driven sub-word units, ii) characters as a unit of learning, and iii) word embeddings learned using a character CNN (Convolution Neural Network). On the tasks of Machine Translation and POS tagging, we found these methods to achieve close to, and occasionally su"},"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":"1709.00616","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T18:45:48Z","cross_cats_sorted":[],"title_canon_sha256":"b4f1ebfbf46bb3bda549d9e47d33433398b5b9c6ca2a6f73ccceb9fd918871f0","abstract_canon_sha256":"4c000e043de378ba7a4fd6138fdb047e234a6a3e0a12f1f4633efa69107b7c5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:07.467143Z","signature_b64":"3Ejz3MzYVLMpgp+EeEhe5euArkK135qvMMWnnaK7jdjZK0FISqzvn/dNS8pwIk5+yEKTwlqA2rs5agHmn9xiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ca273fc09464364c6f1b38c8b75153b5224d8f9349b2a15173687b6cf4fe7b2","last_reissued_at":"2026-05-18T00:36:07.466709Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:07.466709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Abdelali, Fahim Dalvi, Hassan Sajjad, Nadir Durrani, Stephan Vogel, Yonatan Belinkov","submitted_at":"2017-09-02T18:45:48Z","abstract_excerpt":"Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-independent alternatives to morphological segmentation using: i) data-driven sub-word units, ii) characters as a unit of learning, and iii) word embeddings learned using a character CNN (Convolution Neural Network). On the tasks of Machine Translation and POS tagging, we found these methods to achieve close to, and occasionally su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00616","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":"1709.00616","created_at":"2026-05-18T00:36:07.466779+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.00616v1","created_at":"2026-05-18T00:36:07.466779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00616","created_at":"2026-05-18T00:36:07.466779+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSRHH7AJIZBW","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSRHH7AJIZBWJRXR","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSRHH7AJ","created_at":"2026-05-18T12:31:37.085036+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/PSRHH7AJIZBWJRXRWOGIW5IVHN","json":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN.json","graph_json":"https://pith.science/api/pith-number/PSRHH7AJIZBWJRXRWOGIW5IVHN/graph.json","events_json":"https://pith.science/api/pith-number/PSRHH7AJIZBWJRXRWOGIW5IVHN/events.json","paper":"https://pith.science/paper/PSRHH7AJ"},"agent_actions":{"view_html":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN","download_json":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN.json","view_paper":"https://pith.science/paper/PSRHH7AJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.00616&json=true","fetch_graph":"https://pith.science/api/pith-number/PSRHH7AJIZBWJRXRWOGIW5IVHN/graph.json","fetch_events":"https://pith.science/api/pith-number/PSRHH7AJIZBWJRXRWOGIW5IVHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN/action/storage_attestation","attest_author":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN/action/author_attestation","sign_citation":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN/action/citation_signature","submit_replication":"https://pith.science/pith/PSRHH7AJIZBWJRXRWOGIW5IVHN/action/replication_record"}},"created_at":"2026-05-18T00:36:07.466779+00:00","updated_at":"2026-05-18T00:36:07.466779+00:00"}