{"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/hierarchical-transformers-for-multi-document","title":"Hierarchical Transformers for Multi-Document Summarization","arxiv_id":"1905.13164","date":"2019-05-30","proceeding":"ACL 2019 7","authors":["Yang Liu","Mirella Lapata"],"abstract":"In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner. We represent cross-document relationships via an attention mechanism which allows to share information as opposed to simply concatenating text spans and processing them as a flat sequence. Our model learns latent dependencies among textual units, but can also take advantage of explicit graph representations focusing on similarity or discourse relations. Empirical results on the WikiSum dataset demonstrate that the proposed architecture brings substantial improvements over several strong baselines.","url_abs":"https://arxiv.org/abs/1905.13164v1","url_pdf":"https://arxiv.org/pdf/1905.13164v1.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":"hierarchical-transformers-for-multi-document","repo_url":"https://github.com/nlpyang/hiersumm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.13164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.13164"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nlpyang/hiersumm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"14b39c4dc7a42e40","entry":"rouge_results_to_str","repo":"nlpyang/hiersumm","repo_kind":"official","path":"src/abstractive/cal_rouge.py","file_url":"https://github.com/nlpyang/hiersumm/blob/HEAD/src/abstractive/cal_rouge.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14b39c4dc7a42e40"}},{"code_sha256_prefix":"94671955165a864c","entry":"sequence_mask","repo":"nlpyang/hiersumm","repo_kind":"official","path":"src/abstractive/neural.py","file_url":"https://github.com/nlpyang/hiersumm/blob/HEAD/src/abstractive/neural.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94671955165a864c"}},{"code_sha256_prefix":"f017532fc389cbfe","entry":"str2bool","repo":"nlpyang/hiersumm","repo_kind":"official","path":"src/train_abstractive.py","file_url":"https://github.com/nlpyang/hiersumm/blob/HEAD/src/train_abstractive.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f017532fc389cbfe"}},{"code_sha256_prefix":"32488d7d7df6063b","entry":"build_optim","repo":"nlpyang/hiersumm","repo_kind":"official","path":"src/abstractive/optimizer.py","file_url":"https://github.com/nlpyang/hiersumm/blob/HEAD/src/abstractive/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"32488d7d7df6063b"}},{"code_sha256_prefix":"929755107afe4d70","entry":"get_generator","repo":"nlpyang/hiersumm","repo_kind":"official","path":"src/abstractive/model_builder.py","file_url":"https://github.com/nlpyang/hiersumm/blob/HEAD/src/abstractive/model_builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"929755107afe4d70"}},{"code_sha256_prefix":"69b8b31e44791260","entry":"tile","repo":"nlpyang/hiersumm","repo_kind":"official","path":"src/abstractive/neural.py","file_url":"https://github.com/nlpyang/hiersumm/blob/HEAD/src/abstractive/neural.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69b8b31e44791260"}},{"code_sha256_prefix":"9f20e41fbfe40651","entry":"use_gpu","repo":"nlpyang/hiersumm","repo_kind":"official","path":"src/abstractive/optimizer.py","file_url":"https://github.com/nlpyang/hiersumm/blob/HEAD/src/abstractive/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f20e41fbfe40651"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}