{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UVVD2JRF7J4LQRKLINQAWZOPTQ","short_pith_number":"pith:UVVD2JRF","schema_version":"1.0","canonical_sha256":"a56a3d2625fa78b8454b43600b65cf9c3e7fcf9ec8d1c66501c56053b9b0cd9f","source":{"kind":"arxiv","id":"2301.12140","version":1},"attestation_state":"computed","paper":{"title":"Multilingual Sentence Transformer as A Multilingual Word Aligner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanhua Chen, Hanqing Wang, Weikang Wang, Yue Han, Yun Chen","submitted_at":"2023-01-28T09:28:55Z","abstract_excerpt":"Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. In this paper, we investigate whether multilingual sentence Transformer LaBSE is a strong multilingual word aligner. This idea is non-trivial as LaBSE is trained to learn language-agnostic sentence-level embeddings, while the alignment extraction task requires the more fine-grained word-level embeddings to be language-agnostic. We demonstrate that the vanilla LaBSE outperforms other mPLMs currently used in the alignme"},"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":"2301.12140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-28T09:28:55Z","cross_cats_sorted":[],"title_canon_sha256":"ed513f6e21688bf9b99a1ee1b2161bbca7768627ba7e26199a6766b2fecda111","abstract_canon_sha256":"f4f62233ee5166f1b41facf6b5ed99714774a75c503e0686f0aab7f66b3c237a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:35.728066Z","signature_b64":"CXxiMYt2xo6K0lnfNLD7TboJOkXVNg0CIkmbHGbLkj4AFm4hhI2JRJYRNwZmbqqwcOZpfEWJ9E5Vt8tVIp7tCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a56a3d2625fa78b8454b43600b65cf9c3e7fcf9ec8d1c66501c56053b9b0cd9f","last_reissued_at":"2026-07-05T05:36:35.727595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:35.727595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Sentence Transformer as A Multilingual Word Aligner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanhua Chen, Hanqing Wang, Weikang Wang, Yue Han, Yun Chen","submitted_at":"2023-01-28T09:28:55Z","abstract_excerpt":"Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. In this paper, we investigate whether multilingual sentence Transformer LaBSE is a strong multilingual word aligner. This idea is non-trivial as LaBSE is trained to learn language-agnostic sentence-level embeddings, while the alignment extraction task requires the more fine-grained word-level embeddings to be language-agnostic. We demonstrate that the vanilla LaBSE outperforms other mPLMs currently used in the alignme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12140","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/2301.12140/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":"2301.12140","created_at":"2026-07-05T05:36:35.727652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12140v1","created_at":"2026-07-05T05:36:35.727652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12140","created_at":"2026-07-05T05:36:35.727652+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVVD2JRF7J4L","created_at":"2026-07-05T05:36:35.727652+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVVD2JRF7J4LQRKL","created_at":"2026-07-05T05:36:35.727652+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVVD2JRF","created_at":"2026-07-05T05:36:35.727652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03415","citing_title":"SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ","json":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ.json","graph_json":"https://pith.science/api/pith-number/UVVD2JRF7J4LQRKLINQAWZOPTQ/graph.json","events_json":"https://pith.science/api/pith-number/UVVD2JRF7J4LQRKLINQAWZOPTQ/events.json","paper":"https://pith.science/paper/UVVD2JRF"},"agent_actions":{"view_html":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ","download_json":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ.json","view_paper":"https://pith.science/paper/UVVD2JRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12140&json=true","fetch_graph":"https://pith.science/api/pith-number/UVVD2JRF7J4LQRKLINQAWZOPTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UVVD2JRF7J4LQRKLINQAWZOPTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/action/storage_attestation","attest_author":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/action/author_attestation","sign_citation":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/action/citation_signature","submit_replication":"https://pith.science/pith/UVVD2JRF7J4LQRKLINQAWZOPTQ/action/replication_record"}},"created_at":"2026-07-05T05:36:35.727652+00:00","updated_at":"2026-07-05T05:36:35.727652+00:00"}