{"work":{"id":"08e84c2d-86b9-4434-abc7-d78c663567b7","openalex_id":null,"doi":null,"arxiv_id":"2002.10957","raw_key":null,"title":"MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","authors":null,"authors_text":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou","year":2020,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2002.10957","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T13:29:51.318671+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T05:56:11.126997+00:00","updated_at":"2026-07-04T13:29:51.318671+00:00","title_quality_ok":true,"display_title":"MINILM: Deep Self-Attention Distillation for Task- Agnostic Compression of Pre-Trained Transformers","render_title":"MINILM: Deep Self-Attention Distillation for Task- Agnostic Compression of Pre-Trained Transformers"},"hub":{"state":{"work_id":"08e84c2d-86b9-4434-abc7-d78c663567b7","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":28,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2022-01-24T23:36:20+00:00","last_pith_cited_at":"2026-06-25T08:36:43+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-07-06T09:09:02.541841+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}