{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:P4KTWWHQINFHAWUIYZN6QQ3SFE","short_pith_number":"pith:P4KTWWHQ","schema_version":"1.0","canonical_sha256":"7f153b58f0434a705a88c65be843722924d379e512a513b03458bd9c49b2e457","source":{"kind":"arxiv","id":"2112.11740","version":1},"attestation_state":"computed","paper":{"title":"A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changxing Wu, Jinsong Su, Liuwen Cao, Min Zhang, Yang Liu, Yubin Ge","submitted_at":"2021-12-22T09:14:03Z","abstract_excerpt":"Implicit discourse relation recognition (IDRR) is a challenging but crucial task in discourse analysis. Most existing methods train multiple models to predict multi-level labels independently, while ignoring the dependence between hierarchically structured labels. In this paper, we consider multi-level IDRR as a conditional label sequence generation task and propose a Label Dependence-aware Sequence Generation Model (LDSGM) for it. Specifically, we first design a label attentive encoder to learn the global representation of an input instance and its level-specific contexts, where the label dep"},"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":"2112.11740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-22T09:14:03Z","cross_cats_sorted":[],"title_canon_sha256":"9db24d04f471eb6b439185c14e8f2d0d32e9b310936b77551169f5574c6a0c46","abstract_canon_sha256":"1e331d42e321e6c17ad330422e834896a3af01903053f1fea3fd72a837d87f95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:10.446313Z","signature_b64":"HMoDu51cHl094lC5KUw4y672wuDx1AhvJMLwQmSAQkOgbwp7w3LU64wtmCeJgMRNO2M5DgYuVcjP/O77ZeH6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f153b58f0434a705a88c65be843722924d379e512a513b03458bd9c49b2e457","last_reissued_at":"2026-07-05T03:43:10.445875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:10.445875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changxing Wu, Jinsong Su, Liuwen Cao, Min Zhang, Yang Liu, Yubin Ge","submitted_at":"2021-12-22T09:14:03Z","abstract_excerpt":"Implicit discourse relation recognition (IDRR) is a challenging but crucial task in discourse analysis. Most existing methods train multiple models to predict multi-level labels independently, while ignoring the dependence between hierarchically structured labels. In this paper, we consider multi-level IDRR as a conditional label sequence generation task and propose a Label Dependence-aware Sequence Generation Model (LDSGM) for it. Specifically, we first design a label attentive encoder to learn the global representation of an input instance and its level-specific contexts, where the label dep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11740","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/2112.11740/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":"2112.11740","created_at":"2026-07-05T03:43:10.445931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11740v1","created_at":"2026-07-05T03:43:10.445931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11740","created_at":"2026-07-05T03:43:10.445931+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4KTWWHQINFH","created_at":"2026-07-05T03:43:10.445931+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4KTWWHQINFHAWUI","created_at":"2026-07-05T03:43:10.445931+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4KTWWHQ","created_at":"2026-07-05T03:43:10.445931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14880","citing_title":"Leveraging Hierarchical Prototypes as the Verbalizer for Implicit Discourse Relation Recognition","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE","json":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE.json","graph_json":"https://pith.science/api/pith-number/P4KTWWHQINFHAWUIYZN6QQ3SFE/graph.json","events_json":"https://pith.science/api/pith-number/P4KTWWHQINFHAWUIYZN6QQ3SFE/events.json","paper":"https://pith.science/paper/P4KTWWHQ"},"agent_actions":{"view_html":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE","download_json":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE.json","view_paper":"https://pith.science/paper/P4KTWWHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11740&json=true","fetch_graph":"https://pith.science/api/pith-number/P4KTWWHQINFHAWUIYZN6QQ3SFE/graph.json","fetch_events":"https://pith.science/api/pith-number/P4KTWWHQINFHAWUIYZN6QQ3SFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE/action/storage_attestation","attest_author":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE/action/author_attestation","sign_citation":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE/action/citation_signature","submit_replication":"https://pith.science/pith/P4KTWWHQINFHAWUIYZN6QQ3SFE/action/replication_record"}},"created_at":"2026-07-05T03:43:10.445931+00:00","updated_at":"2026-07-05T03:43:10.445931+00:00"}