{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:26HYQV6CT5VSCQEAOIL3OWEYXH","short_pith_number":"pith:26HYQV6C","schema_version":"1.0","canonical_sha256":"d78f8857c29f6b2140807217b75898b9fb409d831852e078ec7837b37cec6446","source":{"kind":"arxiv","id":"2406.13698","version":2},"attestation_state":"computed","paper":{"title":"MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Ge Zhang, Han Wu, Shun Wang, Tyler Loakman, Wenhao Huang","submitted_at":"2024-06-19T16:52:22Z","abstract_excerpt":"Machine Translation (MT) has developed rapidly since the release of Large Language Models and current MT evaluation is performed through comparison with reference human translations or by predicting quality scores from human-labeled data. However, these mainstream evaluation methods mainly focus on fluency and factual reliability, whilst paying little attention to figurative quality. In this paper, we investigate the figurative quality of MT and propose a set of human evaluation metrics focused on the translation of figurative language. We additionally present a multilingual parallel metaphor "},"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":"2406.13698","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T16:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"77dd9ff8ad8127fe4720e5cd3e91bd18c5ce04abf5df63920d63e856e271fda2","abstract_canon_sha256":"4507c11bf0dbd226d02320fac379c0fccaf3f8baae113ffa1b10647190b3c509"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:45.198797Z","signature_b64":"dEtIOFBrnyFznZFAL3A+wy+6e33d8CnqEaKPy3DYb+1dQPUPKn0e0yucUuf9iE6iJkEdRNEODPQ3Hco9QAXyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d78f8857c29f6b2140807217b75898b9fb409d831852e078ec7837b37cec6446","last_reissued_at":"2026-07-05T09:32:45.198261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:45.198261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Ge Zhang, Han Wu, Shun Wang, Tyler Loakman, Wenhao Huang","submitted_at":"2024-06-19T16:52:22Z","abstract_excerpt":"Machine Translation (MT) has developed rapidly since the release of Large Language Models and current MT evaluation is performed through comparison with reference human translations or by predicting quality scores from human-labeled data. However, these mainstream evaluation methods mainly focus on fluency and factual reliability, whilst paying little attention to figurative quality. In this paper, we investigate the figurative quality of MT and propose a set of human evaluation metrics focused on the translation of figurative language. We additionally present a multilingual parallel metaphor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13698","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/2406.13698/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":"2406.13698","created_at":"2026-07-05T09:32:45.198323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13698v2","created_at":"2026-07-05T09:32:45.198323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13698","created_at":"2026-07-05T09:32:45.198323+00:00"},{"alias_kind":"pith_short_12","alias_value":"26HYQV6CT5VS","created_at":"2026-07-05T09:32:45.198323+00:00"},{"alias_kind":"pith_short_16","alias_value":"26HYQV6CT5VSCQEA","created_at":"2026-07-05T09:32:45.198323+00:00"},{"alias_kind":"pith_short_8","alias_value":"26HYQV6C","created_at":"2026-07-05T09:32:45.198323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04299","citing_title":"Searching for Sound-Meaning Collisions: Graph-Based Affordance Retrieval and Multi-Evaluator Ranking for Pun Translation at CLEF 2026 JOKER Task 2","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH","json":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH.json","graph_json":"https://pith.science/api/pith-number/26HYQV6CT5VSCQEAOIL3OWEYXH/graph.json","events_json":"https://pith.science/api/pith-number/26HYQV6CT5VSCQEAOIL3OWEYXH/events.json","paper":"https://pith.science/paper/26HYQV6C"},"agent_actions":{"view_html":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH","download_json":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH.json","view_paper":"https://pith.science/paper/26HYQV6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13698&json=true","fetch_graph":"https://pith.science/api/pith-number/26HYQV6CT5VSCQEAOIL3OWEYXH/graph.json","fetch_events":"https://pith.science/api/pith-number/26HYQV6CT5VSCQEAOIL3OWEYXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH/action/storage_attestation","attest_author":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH/action/author_attestation","sign_citation":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH/action/citation_signature","submit_replication":"https://pith.science/pith/26HYQV6CT5VSCQEAOIL3OWEYXH/action/replication_record"}},"created_at":"2026-07-05T09:32:45.198323+00:00","updated_at":"2026-07-05T09:32:45.198323+00:00"}