{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XVHSSNV55FFS5TWMU5HIMEDHH6","short_pith_number":"pith:XVHSSNV5","schema_version":"1.0","canonical_sha256":"bd4f2936bde94b2ececca74e8610673f8df754446c238eb3917d44d909ac2a8f","source":{"kind":"arxiv","id":"2407.05054","version":1},"attestation_state":"computed","paper":{"title":"Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingshen Zhang, Kailin Zhang, Teng Shen, Wenhe Feng, Wenyu Wang, Xinying Qiu","submitted_at":"2024-07-06T11:56:41Z","abstract_excerpt":"Cross-lingual word alignment plays a crucial role in various natural language processing tasks, particularly for low-resource languages. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-trained language models in low-resource settings. However, their model only considers the similarity of word embedding spaces and does not explicitly model the differences between word embeddings. To address this limitation, we propose incorporating contrastive learning into the BiLSTM-based encoder-decoder framework. Our approach introduces a multi-view negative sampling strategy"},"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":"2407.05054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-06T11:56:41Z","cross_cats_sorted":[],"title_canon_sha256":"63f3916b78e6a90b9a991a02640d22e043a6af4bca33c96eb07a0e98ee059adc","abstract_canon_sha256":"fc9cfe13e221adf6d8b26147559cf2e287750ddd9fc854d6a1e70c812b1a4d2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:07.335513Z","signature_b64":"nLkcFSTBz+/7lkbvI5hT2GrzUjAc0sWZdDTkXl2upG/j4T453D1FF21gcUyboVNE0gN8xagGFO3cYeRH2bBzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4f2936bde94b2ececca74e8610673f8df754446c238eb3917d44d909ac2a8f","last_reissued_at":"2026-07-05T08:41:07.334941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:07.334941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingshen Zhang, Kailin Zhang, Teng Shen, Wenhe Feng, Wenyu Wang, Xinying Qiu","submitted_at":"2024-07-06T11:56:41Z","abstract_excerpt":"Cross-lingual word alignment plays a crucial role in various natural language processing tasks, particularly for low-resource languages. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-trained language models in low-resource settings. However, their model only considers the similarity of word embedding spaces and does not explicitly model the differences between word embeddings. To address this limitation, we propose incorporating contrastive learning into the BiLSTM-based encoder-decoder framework. Our approach introduces a multi-view negative sampling strategy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05054","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/2407.05054/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":"2407.05054","created_at":"2026-07-05T08:41:07.335010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05054v1","created_at":"2026-07-05T08:41:07.335010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05054","created_at":"2026-07-05T08:41:07.335010+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVHSSNV55FFS","created_at":"2026-07-05T08:41:07.335010+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVHSSNV55FFS5TWM","created_at":"2026-07-05T08:41:07.335010+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVHSSNV5","created_at":"2026-07-05T08:41:07.335010+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/XVHSSNV55FFS5TWMU5HIMEDHH6","json":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6.json","graph_json":"https://pith.science/api/pith-number/XVHSSNV55FFS5TWMU5HIMEDHH6/graph.json","events_json":"https://pith.science/api/pith-number/XVHSSNV55FFS5TWMU5HIMEDHH6/events.json","paper":"https://pith.science/paper/XVHSSNV5"},"agent_actions":{"view_html":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6","download_json":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6.json","view_paper":"https://pith.science/paper/XVHSSNV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05054&json=true","fetch_graph":"https://pith.science/api/pith-number/XVHSSNV55FFS5TWMU5HIMEDHH6/graph.json","fetch_events":"https://pith.science/api/pith-number/XVHSSNV55FFS5TWMU5HIMEDHH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6/action/storage_attestation","attest_author":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6/action/author_attestation","sign_citation":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6/action/citation_signature","submit_replication":"https://pith.science/pith/XVHSSNV55FFS5TWMU5HIMEDHH6/action/replication_record"}},"created_at":"2026-07-05T08:41:07.335010+00:00","updated_at":"2026-07-05T08:41:07.335010+00:00"}