{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SXLGONH44NVU4AYFR6GRPMFMKX","short_pith_number":"pith:SXLGONH4","schema_version":"1.0","canonical_sha256":"95d66734fce36b4e03058f8d17b0ac55cdd95dac2235601210c3dea19742e970","source":{"kind":"arxiv","id":"2204.08887","version":1},"attestation_state":"computed","paper":{"title":"Cross-Lingual Phrase Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heqi Zheng, Heyan Huang, Tan Yan, Tian Lan, Wei Wei, Xian-Ling Mao, Xiao Zhang, Zewen Chi","submitted_at":"2022-04-19T13:35:50Z","abstract_excerpt":"Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, how to learn phrase representations for cross-lingual phrase retrieval is still an open problem. In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences. Moreover, we create a large-scale cross-lingual phrase retrieval dataset, which contains 65K bilingual phrase pairs and 4.2M example sentences in 8 En"},"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":"2204.08887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-19T13:35:50Z","cross_cats_sorted":[],"title_canon_sha256":"c54a267dbe89f5de88b95b59cbf7aa039710b461576bdaeeca2b11c8ee9377e5","abstract_canon_sha256":"e3669452b0f86d05a8b6b6f94d371a85226aaae6e4e6e894ba312e37d930e53e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:08.405036Z","signature_b64":"5Jf8I4qLYd092YGSm+G11rmTlRIt/xdfG9nKDpfV0oJpTQy/tfXaaMyTXabvd+rv/dtfFZ9zra+DaR5U76grBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d66734fce36b4e03058f8d17b0ac55cdd95dac2235601210c3dea19742e970","last_reissued_at":"2026-07-05T04:16:08.404566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:08.404566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual Phrase Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heqi Zheng, Heyan Huang, Tan Yan, Tian Lan, Wei Wei, Xian-Ling Mao, Xiao Zhang, Zewen Chi","submitted_at":"2022-04-19T13:35:50Z","abstract_excerpt":"Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, how to learn phrase representations for cross-lingual phrase retrieval is still an open problem. In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences. Moreover, we create a large-scale cross-lingual phrase retrieval dataset, which contains 65K bilingual phrase pairs and 4.2M example sentences in 8 En"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08887","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.08887/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":"2204.08887","created_at":"2026-07-05T04:16:08.404637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08887v1","created_at":"2026-07-05T04:16:08.404637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08887","created_at":"2026-07-05T04:16:08.404637+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXLGONH44NVU","created_at":"2026-07-05T04:16:08.404637+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXLGONH44NVU4AYF","created_at":"2026-07-05T04:16:08.404637+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXLGONH4","created_at":"2026-07-05T04:16:08.404637+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/SXLGONH44NVU4AYFR6GRPMFMKX","json":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX.json","graph_json":"https://pith.science/api/pith-number/SXLGONH44NVU4AYFR6GRPMFMKX/graph.json","events_json":"https://pith.science/api/pith-number/SXLGONH44NVU4AYFR6GRPMFMKX/events.json","paper":"https://pith.science/paper/SXLGONH4"},"agent_actions":{"view_html":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX","download_json":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX.json","view_paper":"https://pith.science/paper/SXLGONH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08887&json=true","fetch_graph":"https://pith.science/api/pith-number/SXLGONH44NVU4AYFR6GRPMFMKX/graph.json","fetch_events":"https://pith.science/api/pith-number/SXLGONH44NVU4AYFR6GRPMFMKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX/action/storage_attestation","attest_author":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX/action/author_attestation","sign_citation":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX/action/citation_signature","submit_replication":"https://pith.science/pith/SXLGONH44NVU4AYFR6GRPMFMKX/action/replication_record"}},"created_at":"2026-07-05T04:16:08.404637+00:00","updated_at":"2026-07-05T04:16:08.404637+00:00"}