{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QSUJPPNYS5BJTC5UUI5NI2YAOZ","short_pith_number":"pith:QSUJPPNY","schema_version":"1.0","canonical_sha256":"84a897bdb89742998bb4a23ad46b00766a82189e6317e273d9c69f244aadbf22","source":{"kind":"arxiv","id":"1702.03814","version":3},"attestation_state":"computed","paper":{"title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Radu Florian, Wael Hamza, Zhiguo Wang","submitted_at":"2017-02-13T15:26:27Z","abstract_excerpt":"Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching. In this work, we propose a bilateral multi-perspective matching (BiMPM) model under the \"matching-aggregation\" framework. Given two sentences $P$ and $Q$, our model first encodes them with a BiLSTM encoder. Next, we match the two encoded sentences in two directions $P \\rightarrow Q$ and $P \\leftarrow Q$. In each matching direction, each time step of one sentence is"},"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":"1702.03814","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-13T15:26:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cb8352971b54da085858a2b15b331567c62e609d3a6e982304c999d871dca7c9","abstract_canon_sha256":"2c78efac83cb2d50214ddda13c7034bc0bc2d5c2b84f46f1f04bca4ad4392afc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:17.353400Z","signature_b64":"7MgoKsPkJu9wvxTASLWZJU11Al42znYI//kAJVHr8YmIBp9JbTdiWnMnYiqNzuxFsrc22/jCa0aLr13cYcEhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84a897bdb89742998bb4a23ad46b00766a82189e6317e273d9c69f244aadbf22","last_reissued_at":"2026-05-18T00:40:17.352642Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:17.352642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Radu Florian, Wael Hamza, Zhiguo Wang","submitted_at":"2017-02-13T15:26:27Z","abstract_excerpt":"Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching. In this work, we propose a bilateral multi-perspective matching (BiMPM) model under the \"matching-aggregation\" framework. Given two sentences $P$ and $Q$, our model first encodes them with a BiLSTM encoder. Next, we match the two encoded sentences in two directions $P \\rightarrow Q$ and $P \\leftarrow Q$. In each matching direction, each time step of one sentence is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03814","kind":"arxiv","version":3},"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":"1702.03814","created_at":"2026-05-18T00:40:17.352765+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.03814v3","created_at":"2026-05-18T00:40:17.352765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03814","created_at":"2026-05-18T00:40:17.352765+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSUJPPNYS5BJ","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSUJPPNYS5BJTC5U","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSUJPPNY","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.05338","citing_title":"To Tune or Not To Tune? How About the Best of Both Worlds?","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00994","citing_title":"Should We Still Pretrain Encoders with Masked Language Modeling?","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2302.09664","citing_title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ","json":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ.json","graph_json":"https://pith.science/api/pith-number/QSUJPPNYS5BJTC5UUI5NI2YAOZ/graph.json","events_json":"https://pith.science/api/pith-number/QSUJPPNYS5BJTC5UUI5NI2YAOZ/events.json","paper":"https://pith.science/paper/QSUJPPNY"},"agent_actions":{"view_html":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ","download_json":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ.json","view_paper":"https://pith.science/paper/QSUJPPNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.03814&json=true","fetch_graph":"https://pith.science/api/pith-number/QSUJPPNYS5BJTC5UUI5NI2YAOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QSUJPPNYS5BJTC5UUI5NI2YAOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ/action/storage_attestation","attest_author":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ/action/author_attestation","sign_citation":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ/action/citation_signature","submit_replication":"https://pith.science/pith/QSUJPPNYS5BJTC5UUI5NI2YAOZ/action/replication_record"}},"created_at":"2026-05-18T00:40:17.352765+00:00","updated_at":"2026-05-18T00:40:17.352765+00:00"}