{"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/ucphrase-unsupervised-context-aware-quality","title":"UCPhrase: Unsupervised Context-aware Quality Phrase Tagging","arxiv_id":"2105.14078","date":"2021-05-28","proceeding":null,"authors":["Xiaotao Gu","Zihan Wang","Zhenyu Bi","Yu Meng","Liyuan Liu","Jiawei Han","Jingbo Shang"],"abstract":"Identifying and understanding quality phrases from context is a fundamental task in text mining. The most challenging part of this task arguably lies in uncommon, emerging, and domain-specific phrases. The infrequent nature of these phrases significantly hurts the performance of phrase mining methods that rely on sufficient phrase occurrences in the input corpus. Context-aware tagging models, though not restricted by frequency, heavily rely on domain experts for either massive sentence-level gold labels or handcrafted gazetteers. In this work, we propose UCPhrase, a novel unsupervised context-aware quality phrase tagger. Specifically, we induce high-quality phrase spans as silver labels from consistently co-occurring word sequences within each document. Compared with typical context-agnostic distant supervision based on existing knowledge bases (KBs), our silver labels root deeply in the input domain and context, thus having unique advantages in preserving contextual completeness and capturing emerging, out-of-KB phrases. Training a conventional neural tagger based on silver labels usually faces the risk of overfitting phrase surface names. Alternatively, we observe that the contextualized attention maps generated from a transformer-based neural language model effectively reveal the connections between words in a surface-agnostic way. Therefore, we pair such attention maps with the silver labels to train a lightweight span prediction model, which can be applied to new input to recognize (unseen) quality phrases regardless of their surface names or frequency. Thorough experiments on various tasks and datasets, including corpus-level phrase ranking, document-level keyphrase extraction, and sentence-level phrase tagging, demonstrate the superiority of our design over state-of-the-art pre-trained, unsupervised, and distantly supervised methods.","url_abs":"https://arxiv.org/abs/2105.14078v1","url_pdf":"https://arxiv.org/pdf/2105.14078v1.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":"ucphrase-unsupervised-context-aware-quality","repo_url":"https://github.com/xgeric/UCPhrase-exp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ucphrase-unsupervised-context-aware-quality","repo_url":"https://github.com/xgeric/UCPhrase-reproduce","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"keyphrase-extraction","task_name":"Keyphrase Extraction"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"phrase-ranking","task_name":"Phrase Ranking"},{"task_slug":"phrase-tagging","task_name":"Phrase Tagging"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset":"KP20k","model":"Wiki+RoBERTa","rank_in_archive_order":1,"of":7,"metrics":{"F1@10":"19.2","Recall":"73.0"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset":"KP20k","model":"UCPhrase","rank_in_archive_order":2,"of":7,"metrics":{"F1@10":"19.7","Recall":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset":"KP20k","model":"AutoPhrase","rank_in_archive_order":3,"of":7,"metrics":{"F1@10":"18.2 ","Recall":"62.9"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset":"KP20k","model":"Spacy","rank_in_archive_order":4,"of":7,"metrics":{"F1@10":"15.3","Recall":"59.5"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset":"KP20k","model":"PKE","rank_in_archive_order":5,"of":7,"metrics":{"F1@10":"12.6","Recall":"57.1"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset":"KP20k","model":"TopMine","rank_in_archive_order":6,"of":7,"metrics":{"F1@10":"15.0","Recall":"53.3"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kp20k","task":"Keyphrase Extraction","dataset":"KP20k","model":"StanfordNLP","rank_in_archive_order":7,"of":7,"metrics":{"F1@10":"13.9","Recall":"51.7"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kptimes","task":"Keyphrase Extraction","dataset":"KPTimes","model":"UCPhrase","rank_in_archive_order":1,"of":4,"metrics":{"F1@10":"10.9","Recall":"83.4"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kptimes","task":"Keyphrase Extraction","dataset":"KPTimes","model":"AutoPhrase","rank_in_archive_order":2,"of":4,"metrics":{"F1@10":"10.3","Recall":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kptimes","task":"Keyphrase Extraction","dataset":"KPTimes","model":"Wiki+RoBERTa","rank_in_archive_order":3,"of":4,"metrics":{"F1@10":"9.4","Recall":"64.5"},"uses_additional_data":false},{"leaderboard":"/sota/keyphrase-extraction-on-kptimes","task":"Keyphrase Extraction","dataset":"KPTimes","model":"TopMine","rank_in_archive_order":4,"of":4,"metrics":{"F1@10":"8.5","Recall":"63.4"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-ranking-on-kp20k","task":"Phrase Ranking","dataset":"KP20k","model":"Wiki+RoBERTa","rank_in_archive_order":1,"of":3,"metrics":{"P@50K":"98.5","P@5K":"100.0"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-ranking-on-kp20k","task":"Phrase Ranking","dataset":"KP20k","model":"UCPhrase","rank_in_archive_order":2,"of":3,"metrics":{"P@50K":"96.5","P@5K":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-ranking-on-kp20k","task":"Phrase Ranking","dataset":"KP20k","model":"TopMine","rank_in_archive_order":3,"of":3,"metrics":{"P@50K":"78.0","P@5K":"81.5"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-ranking-on-kptimes","task":"Phrase Ranking","dataset":"KPTimes","model":"Wiki+RoBERTa","rank_in_archive_order":1,"of":4,"metrics":{"P@50K":" 96.5","P@5K":"99.0"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-ranking-on-kptimes","task":"Phrase Ranking","dataset":"KPTimes","model":"UCPhrase","rank_in_archive_order":2,"of":4,"metrics":{"P@50K":"95.5","P@5K":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-ranking-on-kptimes","task":"Phrase Ranking","dataset":"KPTimes","model":"AutoPhrase","rank_in_archive_order":3,"of":4,"metrics":{"P@50K":"95.5","P@5K":"96.5"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-ranking-on-kptimes","task":"Phrase Ranking","dataset":"KPTimes","model":"TopMine","rank_in_archive_order":4,"of":4,"metrics":{"P@50K":" 71.0","P@5K":"85.5"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kp20k","task":"Phrase Tagging","dataset":"KP20k","model":"UCPhrase","rank_in_archive_order":1,"of":4,"metrics":{"F1":"73.9","Precision":"69.9","Recall":"78.3"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kp20k","task":"Phrase Tagging","dataset":"KP20k","model":"Wiki+RoBERTa","rank_in_archive_order":2,"of":4,"metrics":{"F1":"61.0","Precision":"58.1","Recall":"64.2"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kp20k","task":"Phrase Tagging","dataset":"KP20k","model":"AutoPhrase","rank_in_archive_order":3,"of":4,"metrics":{"F1":"49.7 ","Precision":"55.2","Recall":"45.2"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kp20k","task":"Phrase Tagging","dataset":"KP20k","model":"TopMine","rank_in_archive_order":4,"of":4,"metrics":{"F1":"40.6","Precision":"39.8","Recall":" 41.4"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kptimes","task":"Phrase Tagging","dataset":"KPTimes","model":"UCPhrase","rank_in_archive_order":1,"of":4,"metrics":{"F1":"73.5","Precision":"69.1","Recall":"78.9"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kptimes","task":"Phrase Tagging","dataset":"KPTimes","model":"Wiki+RoBERTa","rank_in_archive_order":2,"of":4,"metrics":{"F1":"63.2","Precision":"60.9","Recall":"65.6"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kptimes","task":"Phrase Tagging","dataset":"KPTimes","model":"AutoPhrase","rank_in_archive_order":3,"of":4,"metrics":{"F1":"45.9","Precision":"44.2","Recall":"47.7"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-tagging-on-kptimes","task":"Phrase Tagging","dataset":"KPTimes","model":"TopMine","rank_in_archive_order":4,"of":4,"metrics":{"F1":"34.0","Precision":"32.0","Recall":"36.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"xgeric/UCPhrase-exp","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xgeric/UCPhrase-reproduce","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b47cf3969d2fed61c51cefd37195909d3d868259073ca60e14471ddc42707399","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}