{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IIDGX56YDYDE5GYAAGD4FQ3BGA","short_pith_number":"pith:IIDGX56Y","schema_version":"1.0","canonical_sha256":"42066bf7d81e064e9b000187c2c361301c3c8a0c6fe21fe878eac679a9a089da","source":{"kind":"arxiv","id":"1908.04812","version":2},"attestation_state":"computed","paper":{"title":"An Effective Domain Adaptive Post-Training Method for BERT in Response Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chanhee Lee, Dongsuk Oh, Dongyub Lee, Heuiseok Lim, Kisu Yang, Taesun Whang","submitted_at":"2019-08-13T18:24:29Z","abstract_excerpt":"We focus on multi-turn response selection in a retrieval-based dialog system. In this paper, we utilize the powerful pre-trained language model Bi-directional Encoder Representations from Transformer (BERT) for a multi-turn dialog system and propose a highly effective post-training method on domain-specific corpus. Although BERT is easily adopted to various NLP tasks and outperforms previous baselines of each task, it still has limitations if a task corpus is too focused on a certain domain. Post-training on domain-specific corpus (e.g., Ubuntu Corpus) helps the model to train contextualized r"},"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":"1908.04812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T18:24:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"55468073e200650ea30467359b175438909c5d4bdc8175d690a219aea3a434ee","abstract_canon_sha256":"659d9c1132253d56b4928cafe80719211a07a87039eafa22aaab7829ae68934f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:14.378139Z","signature_b64":"qW+KjXyle2frHKGYBAC46jsIpMIk9WNwcK/pWS4umVDXXZP5Ghqdg6mKcarDzVPvIcwcefZ15RcRab9pej62AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42066bf7d81e064e9b000187c2c361301c3c8a0c6fe21fe878eac679a9a089da","last_reissued_at":"2026-07-05T01:22:14.377637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:14.377637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Effective Domain Adaptive Post-Training Method for BERT in Response Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chanhee Lee, Dongsuk Oh, Dongyub Lee, Heuiseok Lim, Kisu Yang, Taesun Whang","submitted_at":"2019-08-13T18:24:29Z","abstract_excerpt":"We focus on multi-turn response selection in a retrieval-based dialog system. In this paper, we utilize the powerful pre-trained language model Bi-directional Encoder Representations from Transformer (BERT) for a multi-turn dialog system and propose a highly effective post-training method on domain-specific corpus. Although BERT is easily adopted to various NLP tasks and outperforms previous baselines of each task, it still has limitations if a task corpus is too focused on a certain domain. Post-training on domain-specific corpus (e.g., Ubuntu Corpus) helps the model to train contextualized r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04812","kind":"arxiv","version":2},"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/1908.04812/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":"1908.04812","created_at":"2026-07-05T01:22:14.377702+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04812v2","created_at":"2026-07-05T01:22:14.377702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04812","created_at":"2026-07-05T01:22:14.377702+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIDGX56YDYDE","created_at":"2026-07-05T01:22:14.377702+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIDGX56YDYDE5GYA","created_at":"2026-07-05T01:22:14.377702+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIDGX56Y","created_at":"2026-07-05T01:22:14.377702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04812","citing_title":"An Effective Domain Adaptive Post-Training Method for BERT in Response Selection","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA","json":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA.json","graph_json":"https://pith.science/api/pith-number/IIDGX56YDYDE5GYAAGD4FQ3BGA/graph.json","events_json":"https://pith.science/api/pith-number/IIDGX56YDYDE5GYAAGD4FQ3BGA/events.json","paper":"https://pith.science/paper/IIDGX56Y"},"agent_actions":{"view_html":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA","download_json":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA.json","view_paper":"https://pith.science/paper/IIDGX56Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04812&json=true","fetch_graph":"https://pith.science/api/pith-number/IIDGX56YDYDE5GYAAGD4FQ3BGA/graph.json","fetch_events":"https://pith.science/api/pith-number/IIDGX56YDYDE5GYAAGD4FQ3BGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA/action/storage_attestation","attest_author":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA/action/author_attestation","sign_citation":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA/action/citation_signature","submit_replication":"https://pith.science/pith/IIDGX56YDYDE5GYAAGD4FQ3BGA/action/replication_record"}},"created_at":"2026-07-05T01:22:14.377702+00:00","updated_at":"2026-07-05T01:22:14.377702+00:00"}