{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/generating-edu-extracts-for-plan-guided","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","arxiv_id":"2305.17779","date":"2023-05-28","proceeding":null,"authors":["Griffin Adams","Alexander R. Fabbri","Faisal Ladhak","Kathleen McKeown","Noémie Elhadad"],"abstract":"Two-step approaches, in which summary candidates are generated-then-reranked to return a single summary, can improve ROUGE scores over the standard single-step approach. Yet, standard decoding methods (i.e., beam search, nucleus sampling, and diverse beam search) produce candidates with redundant, and often low quality, content. In this paper, we design a novel method to generate candidates for re-ranking that addresses these issues. We ground each candidate abstract on its own unique content plan and generate distinct plan-guided abstracts using a model's top beam. More concretely, a standard language model (a BART LM) auto-regressively generates elemental discourse unit (EDU) content plans with an extractive copy mechanism. The top K beams from the content plan generator are then used to guide a separate LM, which produces a single abstractive candidate for each distinct plan. We apply an existing re-ranker (BRIO) to abstractive candidates generated from our method, as well as baseline decoding methods. We show large relevance improvements over previously published methods on widely used single document news article corpora, with ROUGE-2 F1 gains of 0.88, 2.01, and 0.38 on CNN / Dailymail, NYT, and Xsum, respectively. A human evaluation on CNN / DM validates these results. Similarly, on 1k samples from CNN / DM, we show that prompting GPT-3 to follow EDU plans outperforms sampling-based methods by 1.05 ROUGE-2 F1 points. Code to generate and realize plans is available at https://github.com/griff4692/edu-sum.","url_abs":"https://arxiv.org/abs/2305.17779v1","url_pdf":"https://arxiv.org/pdf/2305.17779v1.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":[{"paper_slug":"generating-edu-extracts-for-plan-guided","repo_url":"https://github.com/griff4692/edu-sum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"re-ranking","task_name":"Re-Ranking"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.17779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17779"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/griff4692/edu-sum","reach":null}],"summary":{"ran_draft_wrong":4,"ran":2,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":10,"samples":[{"code_sha256_prefix":"d0873cb7263347b8","entry":"_get_ngrams","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0873cb7263347b8"}},{"code_sha256_prefix":"194b802598abbcbb","entry":"_get_word_ngrams","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"194b802598abbcbb"}},{"code_sha256_prefix":"2498cbc3aebe7442","entry":"cal_rouge","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2498cbc3aebe7442"}},{"code_sha256_prefix":"64ecc872e05c4195","entry":"compute_implied","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"64ecc872e05c4195"}},{"code_sha256_prefix":"34dda1ff2147bd09","entry":"edus_from_html","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"34dda1ff2147bd09"}},{"code_sha256_prefix":"d987e6b1911dad9e","entry":"filter_out_extract_tags","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d987e6b1911dad9e"}},{"code_sha256_prefix":"9be35b5988ecd05d","entry":"convert_to_sents","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9be35b5988ecd05d"}},{"code_sha256_prefix":"a9cd10a2e14f3e25","entry":"dialogue_to_sents","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9cd10a2e14f3e25"}},{"code_sha256_prefix":"66d8d1c844a8fc9b","entry":"gain_selection","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66d8d1c844a8fc9b"}},{"code_sha256_prefix":"956c6de86c9e0856","entry":"gen_from_guide","repo":"griff4692/edu-sum","repo_kind":"official","path":"model/gen_from_extract.py","file_url":"https://github.com/griff4692/edu-sum/blob/HEAD/model/gen_from_extract.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"956c6de86c9e0856"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}