{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/closed-book-training-to-improve-summarization","title":"Closed-Book Training to Improve Summarization Encoder Memory","arxiv_id":"1809.04585","date":"2018-09-12","proceeding":"EMNLP 2018 10","authors":["Yichen Jiang","Mohit Bansal"],"abstract":"A good neural sequence-to-sequence summarization model should have a strong\nencoder that can distill and memorize the important information from long input\ntexts so that the decoder can generate salient summaries based on the encoder's\nmemory. In this paper, we aim to improve the memorization capabilities of the\nencoder of a pointer-generator model by adding an additional 'closed-book'\ndecoder without attention and pointer mechanisms. Such a decoder forces the\nencoder to be more selective in the information encoded in its memory state\nbecause the decoder can't rely on the extra information provided by the\nattention and possibly copy modules, and hence improves the entire model. On\nthe CNN/Daily Mail dataset, our 2-decoder model outperforms the baseline\nsignificantly in terms of ROUGE and METEOR metrics, for both cross-entropy and\nreinforced setups (and on human evaluation). Moreover, our model also achieves\nhigher scores in a test-only DUC-2002 generalizability setup. We further\npresent a memory ability test, two saliency metrics, as well as several\nsanity-check ablations (based on fixed-encoder, gradient-flow cut, and model\ncapacity) to prove that the encoder of our 2-decoder model does in fact learn\nstronger memory representations than the baseline encoder.","url_abs":"http://arxiv.org/abs/1809.04585v1","url_pdf":"http://arxiv.org/pdf/1809.04585v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"memorization","task_name":"Memorization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/abstractive-text-summarization-on-cnn-daily","task":"Abstractive Text Summarization","dataset":"CNN / Daily Mail","model":"RL + pg + cbdec","rank_in_archive_order":40,"of":53,"metrics":{"ROUGE-1":"40.66","ROUGE-2":"17.87","ROUGE-L":"37.06"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.04585","atlas_url":"https://app.syntology.ai/?focus=1809.04585","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1809.04585"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.04585\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.04585"},"call":"get_concepts_for_paper(arxiv_id=\"1809.04585\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4838161fbe21b66a35ed3342f2db9770d3890b76eee6071bfcd9cbd171808dd4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}