{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLT3NFKVW26NE76ADCBEW3R3AL","short_pith_number":"pith:KLT3NFKV","schema_version":"1.0","canonical_sha256":"52e7b69555b6bcd27fc018824b6e3b02ed35dfef685192d65372ef2e904bf95a","source":{"kind":"arxiv","id":"2412.08529","version":1},"attestation_state":"computed","paper":{"title":"TECO: Improving Multimodal Intent Recognition with Text Enhancement through Commonsense Knowledge Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cam-Van Thi Nguyen, Lan-Nhi Thi Nguyen, Quynh-Mai Thi Nguyen","submitted_at":"2024-12-11T16:38:48Z","abstract_excerpt":"The objective of multimodal intent recognition (MIR) is to leverage various modalities-such as text, video, and audio-to detect user intentions, which is crucial for understanding human language and context in dialogue systems. Despite advances in this field, two main challenges persist: (1) effectively extracting and utilizing semantic information from robust textual features; (2) aligning and fusing non-verbal modalities with verbal ones effectively. This paper proposes a Text Enhancement with CommOnsense Knowledge Extractor (TECO) to address these challenges. We begin by extracting relation"},"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":"2412.08529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T16:38:48Z","cross_cats_sorted":[],"title_canon_sha256":"26eb8501b02779330541aac353c9865e60cb2ce5f6036037310c8c36797757e3","abstract_canon_sha256":"ae5c9aded7427e950d9f232424420ee7e903a111d0367ce96e79d249e6af53e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:51.613034Z","signature_b64":"yxWUjLHnlxXSQhfnLB6rNsxBQG+cRDYvPkiOGdsgK1ot2wPUAlosSZ8AGfns4s0Q51xv6dVU+s4PZx/SaPLqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52e7b69555b6bcd27fc018824b6e3b02ed35dfef685192d65372ef2e904bf95a","last_reissued_at":"2026-07-05T09:47:51.612629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:51.612629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TECO: Improving Multimodal Intent Recognition with Text Enhancement through Commonsense Knowledge Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cam-Van Thi Nguyen, Lan-Nhi Thi Nguyen, Quynh-Mai Thi Nguyen","submitted_at":"2024-12-11T16:38:48Z","abstract_excerpt":"The objective of multimodal intent recognition (MIR) is to leverage various modalities-such as text, video, and audio-to detect user intentions, which is crucial for understanding human language and context in dialogue systems. Despite advances in this field, two main challenges persist: (1) effectively extracting and utilizing semantic information from robust textual features; (2) aligning and fusing non-verbal modalities with verbal ones effectively. This paper proposes a Text Enhancement with CommOnsense Knowledge Extractor (TECO) to address these challenges. We begin by extracting relation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08529","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/2412.08529/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":"2412.08529","created_at":"2026-07-05T09:47:51.612686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08529v1","created_at":"2026-07-05T09:47:51.612686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08529","created_at":"2026-07-05T09:47:51.612686+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLT3NFKVW26N","created_at":"2026-07-05T09:47:51.612686+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLT3NFKVW26NE76A","created_at":"2026-07-05T09:47:51.612686+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLT3NFKV","created_at":"2026-07-05T09:47:51.612686+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/KLT3NFKVW26NE76ADCBEW3R3AL","json":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL.json","graph_json":"https://pith.science/api/pith-number/KLT3NFKVW26NE76ADCBEW3R3AL/graph.json","events_json":"https://pith.science/api/pith-number/KLT3NFKVW26NE76ADCBEW3R3AL/events.json","paper":"https://pith.science/paper/KLT3NFKV"},"agent_actions":{"view_html":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL","download_json":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL.json","view_paper":"https://pith.science/paper/KLT3NFKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08529&json=true","fetch_graph":"https://pith.science/api/pith-number/KLT3NFKVW26NE76ADCBEW3R3AL/graph.json","fetch_events":"https://pith.science/api/pith-number/KLT3NFKVW26NE76ADCBEW3R3AL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL/action/storage_attestation","attest_author":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL/action/author_attestation","sign_citation":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL/action/citation_signature","submit_replication":"https://pith.science/pith/KLT3NFKVW26NE76ADCBEW3R3AL/action/replication_record"}},"created_at":"2026-07-05T09:47:51.612686+00:00","updated_at":"2026-07-05T09:47:51.612686+00:00"}