{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SF3RHGDBTI3CJSRYFHRA3XQWZC","short_pith_number":"pith:SF3RHGDB","schema_version":"1.0","canonical_sha256":"91771398619a3624ca3829e20dde16c8ab10a66833696fa11ba73cabd1be421c","source":{"kind":"arxiv","id":"1902.05085","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipti Misra Sharma, Irshad Ahmad Bhat, Riyaz Ahmad Bhat","submitted_at":"2019-02-13T19:01:51Z","abstract_excerpt":"We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar, we mitigate"},"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":"1902.05085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-13T19:01:51Z","cross_cats_sorted":[],"title_canon_sha256":"b61105f65942c510521a2bfaf40be9589b08c188c011c26c4e5c377b787827a8","abstract_canon_sha256":"1656f914d752c2c60296b2e1b3cd49f7369bfad291525cbf08d3c15313ebeac8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:01.956008Z","signature_b64":"IohkOVzuCprCgbiiU/8JqkaKE4exxcGeq438DQ6LZEShxdsL11rpO9wx5rSmwGz35VVX/sxQswwIW+zKyBJCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91771398619a3624ca3829e20dde16c8ab10a66833696fa11ba73cabd1be421c","last_reissued_at":"2026-05-17T23:54:01.955363Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:01.955363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipti Misra Sharma, Irshad Ahmad Bhat, Riyaz Ahmad Bhat","submitted_at":"2019-02-13T19:01:51Z","abstract_excerpt":"We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar, we mitigate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05085","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":"1902.05085","created_at":"2026-05-17T23:54:01.955467+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05085v1","created_at":"2026-05-17T23:54:01.955467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05085","created_at":"2026-05-17T23:54:01.955467+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF3RHGDBTI3C","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF3RHGDBTI3CJSRY","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF3RHGDB","created_at":"2026-05-18T12:33:27.125529+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/SF3RHGDBTI3CJSRYFHRA3XQWZC","json":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC.json","graph_json":"https://pith.science/api/pith-number/SF3RHGDBTI3CJSRYFHRA3XQWZC/graph.json","events_json":"https://pith.science/api/pith-number/SF3RHGDBTI3CJSRYFHRA3XQWZC/events.json","paper":"https://pith.science/paper/SF3RHGDB"},"agent_actions":{"view_html":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC","download_json":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC.json","view_paper":"https://pith.science/paper/SF3RHGDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05085&json=true","fetch_graph":"https://pith.science/api/pith-number/SF3RHGDBTI3CJSRYFHRA3XQWZC/graph.json","fetch_events":"https://pith.science/api/pith-number/SF3RHGDBTI3CJSRYFHRA3XQWZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/action/storage_attestation","attest_author":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/action/author_attestation","sign_citation":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/action/citation_signature","submit_replication":"https://pith.science/pith/SF3RHGDBTI3CJSRYFHRA3XQWZC/action/replication_record"}},"created_at":"2026-05-17T23:54:01.955467+00:00","updated_at":"2026-05-17T23:54:01.955467+00:00"}