{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XTEPTQYRNBMG5KV4BJOB6V5OY4","short_pith_number":"pith:XTEPTQYR","schema_version":"1.0","canonical_sha256":"bcc8f9c31168586eaabc0a5c1f57aec70f4ce670e479e27c8c31ecee168c7d63","source":{"kind":"arxiv","id":"1902.10667","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Gap: Attending to Discontinuity in Identification of Multiword Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Le An Ha, Omid Rohanian, Ruslan Mitkov, Samaneh Kouchaki, Shiva Taslimipoor","submitted_at":"2019-02-27T18:01:53Z","abstract_excerpt":"We introduce a new method to tag Multiword Expressions (MWEs) using a linguistically interpretable language-independent deep learning architecture. We specifically target discontinuity, an under-explored aspect that poses a significant challenge to computational treatment of MWEs. Two neural architectures are explored: Graph Convolutional Network (GCN) and multi-head self-attention. GCN leverages dependency parse information, and self-attention attends to long-range relations. We finally propose a combined model that integrates complementary information from both through a gating mechanism. Th"},"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":"1902.10667","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T18:01:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e40a52282d81cb299a7d384eca5ac792300930465aa55a151a29483afa51f95e","abstract_canon_sha256":"5086c71a396b9fb9d19b0a49b87c8efe9425f2000951328613db7cd5941b1fe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:48.297608Z","signature_b64":"KhYAFEoAOjSJ3qi3B+NtmxDCu0vx7inhOU0b+iw3BmqxnbfgJVXF1NcZ7ohikVYtlY07o9l2LS72QP9/CkpBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcc8f9c31168586eaabc0a5c1f57aec70f4ce670e479e27c8c31ecee168c7d63","last_reissued_at":"2026-05-17T23:47:48.296996Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:48.296996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap: Attending to Discontinuity in Identification of Multiword Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Le An Ha, Omid Rohanian, Ruslan Mitkov, Samaneh Kouchaki, Shiva Taslimipoor","submitted_at":"2019-02-27T18:01:53Z","abstract_excerpt":"We introduce a new method to tag Multiword Expressions (MWEs) using a linguistically interpretable language-independent deep learning architecture. We specifically target discontinuity, an under-explored aspect that poses a significant challenge to computational treatment of MWEs. Two neural architectures are explored: Graph Convolutional Network (GCN) and multi-head self-attention. GCN leverages dependency parse information, and self-attention attends to long-range relations. We finally propose a combined model that integrates complementary information from both through a gating mechanism. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10667","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":""},"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":"1902.10667","created_at":"2026-05-17T23:47:48.297087+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10667v2","created_at":"2026-05-17T23:47:48.297087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10667","created_at":"2026-05-17T23:47:48.297087+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTEPTQYRNBMG","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTEPTQYRNBMG5KV4","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTEPTQYR","created_at":"2026-05-18T12:33:33.725879+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/XTEPTQYRNBMG5KV4BJOB6V5OY4","json":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4.json","graph_json":"https://pith.science/api/pith-number/XTEPTQYRNBMG5KV4BJOB6V5OY4/graph.json","events_json":"https://pith.science/api/pith-number/XTEPTQYRNBMG5KV4BJOB6V5OY4/events.json","paper":"https://pith.science/paper/XTEPTQYR"},"agent_actions":{"view_html":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4","download_json":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4.json","view_paper":"https://pith.science/paper/XTEPTQYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10667&json=true","fetch_graph":"https://pith.science/api/pith-number/XTEPTQYRNBMG5KV4BJOB6V5OY4/graph.json","fetch_events":"https://pith.science/api/pith-number/XTEPTQYRNBMG5KV4BJOB6V5OY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4/action/storage_attestation","attest_author":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4/action/author_attestation","sign_citation":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4/action/citation_signature","submit_replication":"https://pith.science/pith/XTEPTQYRNBMG5KV4BJOB6V5OY4/action/replication_record"}},"created_at":"2026-05-17T23:47:48.297087+00:00","updated_at":"2026-05-17T23:47:48.297087+00:00"}