{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EHUEN5YGADKEDNV2JOFLMJGYU","short_pith_number":"pith:6EHUEN5Y","schema_version":"1.0","canonical_sha256":"f10f4237b83006a20db5d25c55b126c51ad22924e40f2aeca66e902cb561a1f6","source":{"kind":"arxiv","id":"2402.02113","version":1},"attestation_state":"computed","paper":{"title":"Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fajri Koto, Iryna Gurevych, Tilman Beck, Timothy Baldwin, Zeerak Talat","submitted_at":"2024-02-03T10:41:05Z","abstract_excerpt":"Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we relax the reliance on texts in low-resource languages by using multilingual lexicons in pretraining to enhance multilingual capabilities. Specifically, we focus on zero-shot sentiment analysis tasks across 34 languages, including 6 high/medium-resource languages, 25 low-resource languages, and 3 code-switching datasets. We demonstrate that pretraining using multilingual lexicons, without using any sentence-level senti"},"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":"2402.02113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T10:41:05Z","cross_cats_sorted":[],"title_canon_sha256":"49b1d3fcfb3eef8221e42e06c39da6c7abb3a855f5f5e3b67512960d2ae42bb5","abstract_canon_sha256":"0201bed399fc7ac3908838a3b70ee1f7106f01fad33010462bdb824f4b953698"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:11.190860Z","signature_b64":"Wz4uiXeSdUTgRNrCzeTOHOkxxuxAKoNL5l9NwYUW+ZNlWyDUml2isHqE0QBH9HLB9o1u8cDNqbvz1qxlKDNbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f10f4237b83006a20db5d25c55b126c51ad22924e40f2aeca66e902cb561a1f6","last_reissued_at":"2026-07-05T07:41:11.190376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:11.190376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fajri Koto, Iryna Gurevych, Tilman Beck, Timothy Baldwin, Zeerak Talat","submitted_at":"2024-02-03T10:41:05Z","abstract_excerpt":"Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we relax the reliance on texts in low-resource languages by using multilingual lexicons in pretraining to enhance multilingual capabilities. Specifically, we focus on zero-shot sentiment analysis tasks across 34 languages, including 6 high/medium-resource languages, 25 low-resource languages, and 3 code-switching datasets. We demonstrate that pretraining using multilingual lexicons, without using any sentence-level senti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02113","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/2402.02113/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":"2402.02113","created_at":"2026-07-05T07:41:11.190433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02113v1","created_at":"2026-07-05T07:41:11.190433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02113","created_at":"2026-07-05T07:41:11.190433+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EHUEN5YGADK","created_at":"2026-07-05T07:41:11.190433+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EHUEN5YGADKEDNV","created_at":"2026-07-05T07:41:11.190433+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EHUEN5Y","created_at":"2026-07-05T07:41:11.190433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09114","citing_title":"Preperiodic points, finiteness, and structures of semigroups of algebraic morphisms","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU","json":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU.json","graph_json":"https://pith.science/api/pith-number/6EHUEN5YGADKEDNV2JOFLMJGYU/graph.json","events_json":"https://pith.science/api/pith-number/6EHUEN5YGADKEDNV2JOFLMJGYU/events.json","paper":"https://pith.science/paper/6EHUEN5Y"},"agent_actions":{"view_html":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU","download_json":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU.json","view_paper":"https://pith.science/paper/6EHUEN5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02113&json=true","fetch_graph":"https://pith.science/api/pith-number/6EHUEN5YGADKEDNV2JOFLMJGYU/graph.json","fetch_events":"https://pith.science/api/pith-number/6EHUEN5YGADKEDNV2JOFLMJGYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU/action/storage_attestation","attest_author":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU/action/author_attestation","sign_citation":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU/action/citation_signature","submit_replication":"https://pith.science/pith/6EHUEN5YGADKEDNV2JOFLMJGYU/action/replication_record"}},"created_at":"2026-07-05T07:41:11.190433+00:00","updated_at":"2026-07-05T07:41:11.190433+00:00"}