{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5FWOQWKALLP26QY374GUOTC7AU","short_pith_number":"pith:5FWOQWKA","schema_version":"1.0","canonical_sha256":"e96ce859405adfaf431bff0d474c5f051eae3bf2166b1043c3e73cfd9cc51a96","source":{"kind":"arxiv","id":"1908.07832","version":2},"attestation_state":"computed","paper":{"title":"Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ahmed El-Kishky, Aston Zhang, Frank Xu, Jiawei Han","submitted_at":"2019-08-18T00:45:16Z","abstract_excerpt":"Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures. Word-level analysis cannot leverage the semantic information present in such subword structures. With regard to word embedding techniques, this leads to not only poor embeddings for infrequent words in long-tailed text corpora but also weak capabilities for handling out-of-vocabulary words. In this paper we propose MorphMine for unsupervised morpheme s"},"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":"1908.07832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-18T00:45:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6aaacbe4ac3598bf3adb10762e684cdad7b0a2bdb035616a5dc8049c5b6818a8","abstract_canon_sha256":"2b09cec59205f8f66a27b3ce60f435b8666f9fc35bdaf045280ccc07c0b6a6a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:10.159402Z","signature_b64":"xzeXdmgut2paWXFeVUWYlpfmalVVWqMDNuDS67poeMfESazoQ6lm9w2i7B/kR7m6FcZbwJbmoLxgLUxDmvY7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e96ce859405adfaf431bff0d474c5f051eae3bf2166b1043c3e73cfd9cc51a96","last_reissued_at":"2026-07-05T00:19:10.158898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:10.158898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ahmed El-Kishky, Aston Zhang, Frank Xu, Jiawei Han","submitted_at":"2019-08-18T00:45:16Z","abstract_excerpt":"Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures. Word-level analysis cannot leverage the semantic information present in such subword structures. With regard to word embedding techniques, this leads to not only poor embeddings for infrequent words in long-tailed text corpora but also weak capabilities for handling out-of-vocabulary words. In this paper we propose MorphMine for unsupervised morpheme s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07832","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/1908.07832/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":"1908.07832","created_at":"2026-07-05T00:19:10.158959+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07832v2","created_at":"2026-07-05T00:19:10.158959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07832","created_at":"2026-07-05T00:19:10.158959+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FWOQWKALLP2","created_at":"2026-07-05T00:19:10.158959+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FWOQWKALLP26QY3","created_at":"2026-07-05T00:19:10.158959+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FWOQWKA","created_at":"2026-07-05T00:19:10.158959+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/5FWOQWKALLP26QY374GUOTC7AU","json":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU.json","graph_json":"https://pith.science/api/pith-number/5FWOQWKALLP26QY374GUOTC7AU/graph.json","events_json":"https://pith.science/api/pith-number/5FWOQWKALLP26QY374GUOTC7AU/events.json","paper":"https://pith.science/paper/5FWOQWKA"},"agent_actions":{"view_html":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU","download_json":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU.json","view_paper":"https://pith.science/paper/5FWOQWKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07832&json=true","fetch_graph":"https://pith.science/api/pith-number/5FWOQWKALLP26QY374GUOTC7AU/graph.json","fetch_events":"https://pith.science/api/pith-number/5FWOQWKALLP26QY374GUOTC7AU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/action/storage_attestation","attest_author":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/action/author_attestation","sign_citation":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/action/citation_signature","submit_replication":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/action/replication_record"}},"created_at":"2026-07-05T00:19:10.158959+00:00","updated_at":"2026-07-05T00:19:10.158959+00:00"}