{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PSRHH7AJIZBWJRXRWOGIW5IVHN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4c000e043de378ba7a4fd6138fdb047e234a6a3e0a12f1f4633efa69107b7c5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T18:45:48Z","title_canon_sha256":"b4f1ebfbf46bb3bda549d9e47d33433398b5b9c6ca2a6f73ccceb9fd918871f0"},"schema_version":"1.0","source":{"id":"1709.00616","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00616","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00616v1","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00616","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"PSRHH7AJIZBW","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PSRHH7AJIZBWJRXR","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PSRHH7AJ","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:0a34c131255b8a7a83a83f022280c7cc6727f1881516cc443df55cd082371634","target":"graph","created_at":"2026-05-18T00:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Ahmed Abdelali, Fahim Dalvi, Hassan Sajjad, Nadir Durrani, Stephan Vogel, Yonatan Belinkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T18:45:48Z","title":"Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00616","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6efb28231adf9428927461cfa5bd1ef11de25c72351ac7b2ca504d2bc822019c","target":"record","created_at":"2026-05-18T00:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4c000e043de378ba7a4fd6138fdb047e234a6a3e0a12f1f4633efa69107b7c5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-02T18:45:48Z","title_canon_sha256":"b4f1ebfbf46bb3bda549d9e47d33433398b5b9c6ca2a6f73ccceb9fd918871f0"},"schema_version":"1.0","source":{"id":"1709.00616","kind":"arxiv","version":1}},"canonical_sha256":"7ca273fc09464364c6f1b38c8b75153b5224d8f9349b2a15173687b6cf4fe7b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ca273fc09464364c6f1b38c8b75153b5224d8f9349b2a15173687b6cf4fe7b2","first_computed_at":"2026-05-18T00:36:07.466709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:07.466709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Ejz3MzYVLMpgp+EeEhe5euArkK135qvMMWnnaK7jdjZK0FISqzvn/dNS8pwIk5+yEKTwlqA2rs5agHmn9xiBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:07.467143Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00616","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6efb28231adf9428927461cfa5bd1ef11de25c72351ac7b2ca504d2bc822019c","sha256:0a34c131255b8a7a83a83f022280c7cc6727f1881516cc443df55cd082371634"],"state_sha256":"b6688547b6a4d1e2f2f8a321088ae50a498ea6f348f53afe8ab1a58bbb95fc62"}