{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4FRW2AUAKMXJ47JQHH47KQDRFU","short_pith_number":"pith:4FRW2AUA","schema_version":"1.0","canonical_sha256":"e1636d0280532e9e7d3039f9f540712d3daabfce953efc14ea069ecac85b3b6a","source":{"kind":"arxiv","id":"1706.01740","version":1},"attestation_state":"computed","paper":{"title":"Label-Dependencies Aware Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isabelle Tellier, Marco Dinarelli, Yoann Dupont","submitted_at":"2017-06-06T13:10:49Z","abstract_excerpt":"In the last few years, Recurrent Neural Networks (RNNs) have proved effective on several NLP tasks. Despite such great success, their ability to model \\emph{sequence labeling} is still limited. This lead research toward solutions where RNNs are combined with models which already proved effective in this domain, such as CRFs. In this work we propose a solution far simpler but very effective: an evolution of the simple Jordan RNN, where labels are re-injected as input into the network, and converted into embeddings, in the same way as words. We compare this RNN variant to all the other RNN model"},"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":"1706.01740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-06T13:10:49Z","cross_cats_sorted":[],"title_canon_sha256":"be88efb5e697ba8b77b5359a81a3a366deafd3d7ca4b29d42a18ebc48b2733f7","abstract_canon_sha256":"72e1ff56cd7731a687cbb6c1867ac196b671e59890d06c88049bf2eea1d441e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:56.109426Z","signature_b64":"AXa+F/hxIYGI6lGd1wUHuQZWmpyqIPWgIDpyaMD9jzSwqNA8MJOX0AB9IXN+1pLbBoWuCU7Jtd8rbhkQ/VhYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1636d0280532e9e7d3039f9f540712d3daabfce953efc14ea069ecac85b3b6a","last_reissued_at":"2026-05-18T00:42:56.108729Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:56.108729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-Dependencies Aware Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isabelle Tellier, Marco Dinarelli, Yoann Dupont","submitted_at":"2017-06-06T13:10:49Z","abstract_excerpt":"In the last few years, Recurrent Neural Networks (RNNs) have proved effective on several NLP tasks. Despite such great success, their ability to model \\emph{sequence labeling} is still limited. This lead research toward solutions where RNNs are combined with models which already proved effective in this domain, such as CRFs. In this work we propose a solution far simpler but very effective: an evolution of the simple Jordan RNN, where labels are re-injected as input into the network, and converted into embeddings, in the same way as words. We compare this RNN variant to all the other RNN model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01740","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":"1706.01740","created_at":"2026-05-18T00:42:56.108851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01740v1","created_at":"2026-05-18T00:42:56.108851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01740","created_at":"2026-05-18T00:42:56.108851+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FRW2AUAKMXJ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FRW2AUAKMXJ47JQ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FRW2AUA","created_at":"2026-05-18T12:30:58.224056+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/4FRW2AUAKMXJ47JQHH47KQDRFU","json":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU.json","graph_json":"https://pith.science/api/pith-number/4FRW2AUAKMXJ47JQHH47KQDRFU/graph.json","events_json":"https://pith.science/api/pith-number/4FRW2AUAKMXJ47JQHH47KQDRFU/events.json","paper":"https://pith.science/paper/4FRW2AUA"},"agent_actions":{"view_html":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU","download_json":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU.json","view_paper":"https://pith.science/paper/4FRW2AUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01740&json=true","fetch_graph":"https://pith.science/api/pith-number/4FRW2AUAKMXJ47JQHH47KQDRFU/graph.json","fetch_events":"https://pith.science/api/pith-number/4FRW2AUAKMXJ47JQHH47KQDRFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU/action/storage_attestation","attest_author":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU/action/author_attestation","sign_citation":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU/action/citation_signature","submit_replication":"https://pith.science/pith/4FRW2AUAKMXJ47JQHH47KQDRFU/action/replication_record"}},"created_at":"2026-05-18T00:42:56.108851+00:00","updated_at":"2026-05-18T00:42:56.108851+00:00"}