{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KCUIBMWURYHPVBCJSP3OT5WJHI","short_pith_number":"pith:KCUIBMWU","schema_version":"1.0","canonical_sha256":"50a880b2d48e0efa844993f6e9f6c93a373d3e586a28f4c3815ba8a8c666f1f0","source":{"kind":"arxiv","id":"1808.02772","version":2},"attestation_state":"computed","paper":{"title":"Effective Character-augmented Word Embedding for Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Pengfei Zhu, Yafang Huang, Zhuosheng Zhang","submitted_at":"2018-08-07T15:37:20Z","abstract_excerpt":"Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate word and character level representations, which has been shown suboptimal for the concerned task. In this paper, we empirically explore different integration strategies of word and character embeddings and propose a character-augmented reader which attends character-level representation to augment word embedding with a short list to improve word representations, especially for rare words. Experimental results show that "},"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":"1808.02772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-07T15:37:20Z","cross_cats_sorted":[],"title_canon_sha256":"fa49e1fe9b0087b0643ff44c289402195573ec90e74fa52c5a3d78d9c1c02843","abstract_canon_sha256":"1514a8ad6cacf31d9950d1c2ecfcd026882e83676893bf5203188b1446c4ad2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:04.479185Z","signature_b64":"2thYHRWHUxurkRHDLRM9BjBIrte9kNpSu4QIYcYlFyZfDn7piufE2pZVmFVpR3Vk3dFfzee0APv/FWRYtaBaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50a880b2d48e0efa844993f6e9f6c93a373d3e586a28f4c3815ba8a8c666f1f0","last_reissued_at":"2026-07-05T02:05:04.478763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:04.478763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Character-augmented Word Embedding for Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Pengfei Zhu, Yafang Huang, Zhuosheng Zhang","submitted_at":"2018-08-07T15:37:20Z","abstract_excerpt":"Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate word and character level representations, which has been shown suboptimal for the concerned task. In this paper, we empirically explore different integration strategies of word and character embeddings and propose a character-augmented reader which attends character-level representation to augment word embedding with a short list to improve word representations, especially for rare words. Experimental results show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02772","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/1808.02772/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":"1808.02772","created_at":"2026-07-05T02:05:04.478818+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02772v2","created_at":"2026-07-05T02:05:04.478818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02772","created_at":"2026-07-05T02:05:04.478818+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCUIBMWURYHP","created_at":"2026-07-05T02:05:04.478818+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCUIBMWURYHPVBCJ","created_at":"2026-07-05T02:05:04.478818+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCUIBMWU","created_at":"2026-07-05T02:05:04.478818+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/KCUIBMWURYHPVBCJSP3OT5WJHI","json":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI.json","graph_json":"https://pith.science/api/pith-number/KCUIBMWURYHPVBCJSP3OT5WJHI/graph.json","events_json":"https://pith.science/api/pith-number/KCUIBMWURYHPVBCJSP3OT5WJHI/events.json","paper":"https://pith.science/paper/KCUIBMWU"},"agent_actions":{"view_html":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI","download_json":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI.json","view_paper":"https://pith.science/paper/KCUIBMWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02772&json=true","fetch_graph":"https://pith.science/api/pith-number/KCUIBMWURYHPVBCJSP3OT5WJHI/graph.json","fetch_events":"https://pith.science/api/pith-number/KCUIBMWURYHPVBCJSP3OT5WJHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI/action/storage_attestation","attest_author":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI/action/author_attestation","sign_citation":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI/action/citation_signature","submit_replication":"https://pith.science/pith/KCUIBMWURYHPVBCJSP3OT5WJHI/action/replication_record"}},"created_at":"2026-07-05T02:05:04.478818+00:00","updated_at":"2026-07-05T02:05:04.478818+00:00"}