{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6NFKCXSEUKOB2D5HYM2XFQZ3TZ","short_pith_number":"pith:6NFKCXSE","schema_version":"1.0","canonical_sha256":"f34aa15e44a29c1d0fa7c33572c33b9e6895b1de9c6051e5d817cf5941d75c58","source":{"kind":"arxiv","id":"1904.09491","version":2},"attestation_state":"computed","paper":{"title":"Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"2), (2) Linagora, 3), (3) AUEB), Antoine Jean-Pierre Tixier (1), Guokan Shang (1, Jean-Pierre Lorr\\'e (2) ((1) \\'Ecole Polytechnique, Michalis Vazirgiannis (1","submitted_at":"2019-04-20T20:01:52Z","abstract_excerpt":"Abstractive community detection is an important spoken language understanding task, whose goal is to group utterances in a conversation according to whether they can be jointly summarized by a common abstractive sentence. This paper provides a novel approach to this task. We first introduce a neural contextual utterance encoder featuring three types of self-attention mechanisms. We then train it using the siamese and triplet energy-based meta-architectures. Experiments on the AMI corpus show that our system outperforms multiple energy-based and non-energy based baselines from the state-of-the-"},"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":"1904.09491","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-20T20:01:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1d9c27ed5ad806961b487e6b6ce1902480cb7c1f6e2b70af61e33cb756601a2","abstract_canon_sha256":"eafab046fa53aeab40095845a28ff09d21839eaad2784790fcdf2dcf2107b99f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:50.913016Z","signature_b64":"wz1xP28t11FsFNhp5t03DKXkBMuVSB38jvRxw6/2MQI6v3DM6ciec69f97na+iSC06RRHROs3XVjaNGyvVN/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f34aa15e44a29c1d0fa7c33572c33b9e6895b1de9c6051e5d817cf5941d75c58","last_reissued_at":"2026-07-05T00:17:50.912584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:50.912584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"2), (2) Linagora, 3), (3) AUEB), Antoine Jean-Pierre Tixier (1), Guokan Shang (1, Jean-Pierre Lorr\\'e (2) ((1) \\'Ecole Polytechnique, Michalis Vazirgiannis (1","submitted_at":"2019-04-20T20:01:52Z","abstract_excerpt":"Abstractive community detection is an important spoken language understanding task, whose goal is to group utterances in a conversation according to whether they can be jointly summarized by a common abstractive sentence. This paper provides a novel approach to this task. We first introduce a neural contextual utterance encoder featuring three types of self-attention mechanisms. We then train it using the siamese and triplet energy-based meta-architectures. Experiments on the AMI corpus show that our system outperforms multiple energy-based and non-energy based baselines from the state-of-the-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09491","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/1904.09491/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":"1904.09491","created_at":"2026-07-05T00:17:50.912640+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09491v2","created_at":"2026-07-05T00:17:50.912640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09491","created_at":"2026-07-05T00:17:50.912640+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NFKCXSEUKOB","created_at":"2026-07-05T00:17:50.912640+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NFKCXSEUKOB2D5H","created_at":"2026-07-05T00:17:50.912640+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NFKCXSE","created_at":"2026-07-05T00:17:50.912640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.09334","citing_title":"LinTO : Assistant vocal open-source respectueux des donn\\'ees personnelles pour les r\\'eunions d'entreprise","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"1907.11769","citing_title":"Automatically Learning Construction Injury Precursors from Text","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ","json":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ.json","graph_json":"https://pith.science/api/pith-number/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/graph.json","events_json":"https://pith.science/api/pith-number/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/events.json","paper":"https://pith.science/paper/6NFKCXSE"},"agent_actions":{"view_html":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ","download_json":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ.json","view_paper":"https://pith.science/paper/6NFKCXSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09491&json=true","fetch_graph":"https://pith.science/api/pith-number/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/action/storage_attestation","attest_author":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/action/author_attestation","sign_citation":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/action/citation_signature","submit_replication":"https://pith.science/pith/6NFKCXSEUKOB2D5HYM2XFQZ3TZ/action/replication_record"}},"created_at":"2026-07-05T00:17:50.912640+00:00","updated_at":"2026-07-05T00:17:50.912640+00:00"}