{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3CAISQAG57JRQXHJKVSNODBBLF","short_pith_number":"pith:3CAISQAG","schema_version":"1.0","canonical_sha256":"d880894006efd3185ce95564d70c215940950773b78bc6208e88d18b9c74ad9d","source":{"kind":"arxiv","id":"2002.03049","version":1},"attestation_state":"computed","paper":{"title":"Snippext: Semi-supervised Opinion Mining with Augmented Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Wang-Chiew Tan, Xiaolan Wang, Yuliang Li, Zhengjie Miao","submitted_at":"2020-02-07T23:54:23Z","abstract_excerpt":"Online services are interested in solutions to opinion mining, which is the problem of extracting aspects, opinions, and sentiments from text. One method to mine opinions is to leverage the recent success of pre-trained language models which can be fine-tuned to obtain high-quality extractions from reviews. However, fine-tuning language models still requires a non-trivial amount of training data. In this paper, we study the problem of how to significantly reduce the amount of labeled training data required in fine-tuning language models for opinion mining. We describe Snippext, an opinion mini"},"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":"2002.03049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-07T23:54:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29533d417e2335bfb38cfde98210f86958659c56ebe1b9c144f0db438ee6219d","abstract_canon_sha256":"ceddf2079ecea5a3f6324190395085e2dcc0724a1f0eabfa0d628aa234b0d197"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:18.413936Z","signature_b64":"TaByaXKOCmtQBw9P4pT6gULPNHjhzFuoWJt8TnXKWkpK/qlxFOisX9mQ05kS2CEg+/dXtjvym3CnXZahKv5vBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d880894006efd3185ce95564d70c215940950773b78bc6208e88d18b9c74ad9d","last_reissued_at":"2026-07-05T00:39:18.413489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:18.413489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Snippext: Semi-supervised Opinion Mining with Augmented Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Wang-Chiew Tan, Xiaolan Wang, Yuliang Li, Zhengjie Miao","submitted_at":"2020-02-07T23:54:23Z","abstract_excerpt":"Online services are interested in solutions to opinion mining, which is the problem of extracting aspects, opinions, and sentiments from text. One method to mine opinions is to leverage the recent success of pre-trained language models which can be fine-tuned to obtain high-quality extractions from reviews. However, fine-tuning language models still requires a non-trivial amount of training data. In this paper, we study the problem of how to significantly reduce the amount of labeled training data required in fine-tuning language models for opinion mining. We describe Snippext, an opinion mini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03049","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.03049/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":"2002.03049","created_at":"2026-07-05T00:39:18.413556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.03049v1","created_at":"2026-07-05T00:39:18.413556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03049","created_at":"2026-07-05T00:39:18.413556+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CAISQAG57JR","created_at":"2026-07-05T00:39:18.413556+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CAISQAG57JRQXHJ","created_at":"2026-07-05T00:39:18.413556+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CAISQAG","created_at":"2026-07-05T00:39:18.413556+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/3CAISQAG57JRQXHJKVSNODBBLF","json":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF.json","graph_json":"https://pith.science/api/pith-number/3CAISQAG57JRQXHJKVSNODBBLF/graph.json","events_json":"https://pith.science/api/pith-number/3CAISQAG57JRQXHJKVSNODBBLF/events.json","paper":"https://pith.science/paper/3CAISQAG"},"agent_actions":{"view_html":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF","download_json":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF.json","view_paper":"https://pith.science/paper/3CAISQAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.03049&json=true","fetch_graph":"https://pith.science/api/pith-number/3CAISQAG57JRQXHJKVSNODBBLF/graph.json","fetch_events":"https://pith.science/api/pith-number/3CAISQAG57JRQXHJKVSNODBBLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF/action/storage_attestation","attest_author":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF/action/author_attestation","sign_citation":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF/action/citation_signature","submit_replication":"https://pith.science/pith/3CAISQAG57JRQXHJKVSNODBBLF/action/replication_record"}},"created_at":"2026-07-05T00:39:18.413556+00:00","updated_at":"2026-07-05T00:39:18.413556+00:00"}