{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NYSNTHKXJOTH7GEPUVXLEOZBPR","short_pith_number":"pith:NYSNTHKX","schema_version":"1.0","canonical_sha256":"6e24d99d574ba67f988fa56eb23b217c46fec4a1756dd76edb7092f6c0a97195","source":{"kind":"arxiv","id":"1808.09551","version":1},"attestation_state":"computed","paper":{"title":"Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fr\\'ederic Godin, Joni Dambre, Kris Demuynck, Thomas Demeester, Wesley De Neve","submitted_at":"2018-08-28T21:44:26Z","abstract_excerpt":"Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us "},"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":"1808.09551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T21:44:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"092c000f159fca41f44c6263bbb5d38d8c7f22f183e176b0e02148058ca3aebf","abstract_canon_sha256":"db713acd654b9136832af5f4597b369a02a8e41f21d987d0e14fe66065515f56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:55.232236Z","signature_b64":"79s5yFR/3cRTBO3Nx/VlfPXgsvLgJkmqKTgEuLNopWBM0+GfNRcQlB+h8Y/2FA88Ea1JAjB05JwwkYvLP4dWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e24d99d574ba67f988fa56eb23b217c46fec4a1756dd76edb7092f6c0a97195","last_reissued_at":"2026-05-18T00:06:55.231544Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:55.231544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fr\\'ederic Godin, Joni Dambre, Kris Demuynck, Thomas Demeester, Wesley De Neve","submitted_at":"2018-08-28T21:44:26Z","abstract_excerpt":"Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09551","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":""},"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":"1808.09551","created_at":"2026-05-18T00:06:55.231666+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09551v1","created_at":"2026-05-18T00:06:55.231666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09551","created_at":"2026-05-18T00:06:55.231666+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYSNTHKXJOTH","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYSNTHKXJOTH7GEP","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYSNTHKX","created_at":"2026-05-18T12:32:40.477152+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/NYSNTHKXJOTH7GEPUVXLEOZBPR","json":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR.json","graph_json":"https://pith.science/api/pith-number/NYSNTHKXJOTH7GEPUVXLEOZBPR/graph.json","events_json":"https://pith.science/api/pith-number/NYSNTHKXJOTH7GEPUVXLEOZBPR/events.json","paper":"https://pith.science/paper/NYSNTHKX"},"agent_actions":{"view_html":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR","download_json":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR.json","view_paper":"https://pith.science/paper/NYSNTHKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09551&json=true","fetch_graph":"https://pith.science/api/pith-number/NYSNTHKXJOTH7GEPUVXLEOZBPR/graph.json","fetch_events":"https://pith.science/api/pith-number/NYSNTHKXJOTH7GEPUVXLEOZBPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR/action/storage_attestation","attest_author":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR/action/author_attestation","sign_citation":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR/action/citation_signature","submit_replication":"https://pith.science/pith/NYSNTHKXJOTH7GEPUVXLEOZBPR/action/replication_record"}},"created_at":"2026-05-18T00:06:55.231666+00:00","updated_at":"2026-05-18T00:06:55.231666+00:00"}