{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z5CNCVF3C5C4KD2FL2EDWNK2M6","short_pith_number":"pith:Z5CNCVF3","schema_version":"1.0","canonical_sha256":"cf44d154bb1745c50f455e883b355a67892ba03a2cd65bfd43b10edfe3a53eaf","source":{"kind":"arxiv","id":"2109.09894","version":1},"attestation_state":"computed","paper":{"title":"Representation Learning for Short Text Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyan Huang, Hui Yin, Jianxin Li, Shuiqiao Yang, Xiangyu Song","submitted_at":"2021-09-21T00:30:24Z","abstract_excerpt":"Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the expressiveness for short text representations with more condensed, low-dimensional and continuous features compared to the traditional Bag-of-Words (BoW) model. However, these models are trained for general purposes and thus are suboptimal for the short text clustering task. In this paper, we propose two methods to exploit the unsupervised autoencoder (AE) framework "},"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":"2109.09894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T00:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"4050a1a3e88243627b07287ddff44cada111ebab29f88a9ada0d194520ca53a3","abstract_canon_sha256":"c688c1701ffa37176ecf440414133cb74dadda1c1e0e1686b42d6a585664b952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:55.559851Z","signature_b64":"15bpdkosNQsH5212ob3e1tUGCxuv21K+SBdkqqVYgxJCDFdrbyEoxH/B5kOGbznf8UuGlB15mke2/v12RhnSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf44d154bb1745c50f455e883b355a67892ba03a2cd65bfd43b10edfe3a53eaf","last_reissued_at":"2026-07-05T03:15:55.559389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:55.559389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Learning for Short Text Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyan Huang, Hui Yin, Jianxin Li, Shuiqiao Yang, Xiangyu Song","submitted_at":"2021-09-21T00:30:24Z","abstract_excerpt":"Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the expressiveness for short text representations with more condensed, low-dimensional and continuous features compared to the traditional Bag-of-Words (BoW) model. However, these models are trained for general purposes and thus are suboptimal for the short text clustering task. In this paper, we propose two methods to exploit the unsupervised autoencoder (AE) framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09894","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/2109.09894/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":"2109.09894","created_at":"2026-07-05T03:15:55.559461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09894v1","created_at":"2026-07-05T03:15:55.559461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09894","created_at":"2026-07-05T03:15:55.559461+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5CNCVF3C5C4","created_at":"2026-07-05T03:15:55.559461+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5CNCVF3C5C4KD2F","created_at":"2026-07-05T03:15:55.559461+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5CNCVF3","created_at":"2026-07-05T03:15:55.559461+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/Z5CNCVF3C5C4KD2FL2EDWNK2M6","json":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6.json","graph_json":"https://pith.science/api/pith-number/Z5CNCVF3C5C4KD2FL2EDWNK2M6/graph.json","events_json":"https://pith.science/api/pith-number/Z5CNCVF3C5C4KD2FL2EDWNK2M6/events.json","paper":"https://pith.science/paper/Z5CNCVF3"},"agent_actions":{"view_html":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6","download_json":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6.json","view_paper":"https://pith.science/paper/Z5CNCVF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09894&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5CNCVF3C5C4KD2FL2EDWNK2M6/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5CNCVF3C5C4KD2FL2EDWNK2M6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/action/storage_attestation","attest_author":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/action/author_attestation","sign_citation":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/action/citation_signature","submit_replication":"https://pith.science/pith/Z5CNCVF3C5C4KD2FL2EDWNK2M6/action/replication_record"}},"created_at":"2026-07-05T03:15:55.559461+00:00","updated_at":"2026-07-05T03:15:55.559461+00:00"}