{"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/twag-a-topic-guided-wikipedia-abstract","title":"TWAG: A Topic-Guided Wikipedia Abstract Generator","arxiv_id":"2106.15135","date":"2021-06-29","proceeding":"ACL 2021 5","authors":["Fangwei Zhu","Shangqing Tu","Jiaxin Shi","Juanzi Li","Lei Hou","Tong Cui"],"abstract":"Wikipedia abstract generation aims to distill a Wikipedia abstract from web sources and has met significant success by adopting multi-document summarization techniques. However, previous works generally view the abstract as plain text, ignoring the fact that it is a description of a certain entity and can be decomposed into different topics. In this paper, we propose a two-stage model TWAG that guides the abstract generation with topical information. First, we detect the topic of each input paragraph with a classifier trained on existing Wikipedia articles to divide input documents into different topics. Then, we predict the topic distribution of each abstract sentence, and decode the sentence from topic-aware representations with a Pointer-Generator network. We evaluate our model on the WikiCatSum dataset, and the results show that \\modelnames outperforms various existing baselines and is capable of generating comprehensive abstracts. Our code and dataset can be accessed at \\url{https://github.com/THU-KEG/TWAG}","url_abs":"https://arxiv.org/abs/2106.15135v1","url_pdf":"https://arxiv.org/pdf/2106.15135v1.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":"twag-a-topic-guided-wikipedia-abstract","repo_url":"https://github.com/THU-KEG/TWAG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"abstract-generation","task_name":"Abstract generation"},{"task_slug":"articles","task_name":"Articles"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.15135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.15135"}},"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/THU-KEG/TWAG","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"1aaafb7fbdb31aba","entry":"Beam","repo":"THU-KEG/TWAG","repo_kind":"official","path":"src/c_generate_soft/model.py","file_url":"https://github.com/THU-KEG/TWAG/blob/HEAD/src/c_generate_soft/model.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":"1aaafb7fbdb31aba"}},{"code_sha256_prefix":"89108c1b79aa9aab","entry":"BiGRUEncoder","repo":"THU-KEG/TWAG","repo_kind":"official","path":"src/c_generate_soft/model.py","file_url":"https://github.com/THU-KEG/TWAG/blob/HEAD/src/c_generate_soft/model.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":"89108c1b79aa9aab"}},{"code_sha256_prefix":"8b3903c33752a72b","entry":"DocumentDecoder","repo":"THU-KEG/TWAG","repo_kind":"official","path":"src/c_generate_soft/model.py","file_url":"https://github.com/THU-KEG/TWAG/blob/HEAD/src/c_generate_soft/model.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":"8b3903c33752a72b"}},{"code_sha256_prefix":"93229e6b24f7c809","entry":"PointerGenerator","repo":"THU-KEG/TWAG","repo_kind":"official","path":"src/c_generate_soft/model.py","file_url":"https://github.com/THU-KEG/TWAG/blob/HEAD/src/c_generate_soft/model.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":"93229e6b24f7c809"}},{"code_sha256_prefix":"faaab31d5f11ab68","entry":"TopicDecodeModel","repo":"THU-KEG/TWAG","repo_kind":"official","path":"src/c_generate_soft/model.py","file_url":"https://github.com/THU-KEG/TWAG/blob/HEAD/src/c_generate_soft/model.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":"faaab31d5f11ab68"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}