{"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/summarizing-community-based-question-answer","title":"Summarizing Community-based Question-Answer Pairs","arxiv_id":"2211.09892","date":"2022-11-17","proceeding":null,"authors":["Ting-Yao Hsu","Yoshi Suhara","Xiaolan Wang"],"abstract":"Community-based Question Answering (CQA), which allows users to acquire their desired information, has increasingly become an essential component of online services in various domains such as E-commerce, travel, and dining. However, an overwhelming number of CQA pairs makes it difficult for users without particular intent to find useful information spread over CQA pairs. To help users quickly digest the key information, we propose the novel CQA summarization task that aims to create a concise summary from CQA pairs. To this end, we first design a multi-stage data annotation process and create a benchmark dataset, CoQASUM, based on the Amazon QA corpus. We then compare a collection of extractive and abstractive summarization methods and establish a strong baseline approach DedupLED for the CQA summarization task. Our experiment further confirms two key challenges, sentence-type transfer and deduplication removal, towards the CQA summarization task. Our data and code are publicly available.","url_abs":"https://arxiv.org/abs/2211.09892v1","url_pdf":"https://arxiv.org/pdf/2211.09892v1.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":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.09892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09892"}},"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/nlpyang/BertSum","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":1,"ran_violates":1,"unverified":4},"by_repo_kind":{"found_in_text":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"66575e439195e14f","entry":"all_gather_list","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/distributed.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/distributed.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":"66575e439195e14f"}},{"code_sha256_prefix":"8d23fbe2b99b840b","entry":"gelu","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/models/neural.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/models/neural.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"code_sha256_prefix":"b80220994c939e73","entry":"is_master","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/distributed.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/distributed.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":"b80220994c939e73"}},{"code_sha256_prefix":"f017532fc389cbfe","entry":"str2bool","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/preprocess.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/preprocess.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":"89e1b4954fded05b","entry":"build_optim","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/models/optimizers.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/models/optimizers.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":"89e1b4954fded05b"}},{"code_sha256_prefix":"e317b188410c9032","entry":"init_logger","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/others/logging.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/others/logging.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":"e317b188410c9032"}},{"code_sha256_prefix":"ab84694a81d67283","entry":"simple_batch_size_fn","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/models/data_loader.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/models/data_loader.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":"ab84694a81d67283"}},{"code_sha256_prefix":"9f20e41fbfe40651","entry":"use_gpu","repo":"nlpyang/BertSum","repo_kind":"found_in_text","path":"src/models/optimizers.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/models/optimizers.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}