{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T06:10:07Z","timestamp":1755843007640,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Science Foundation","award":["2229612"],"award-info":[{"award-number":["2229612"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657681","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2806-2810","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TextData: Save What You Know and Find What You Don't"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0961-2694","authenticated-orcid":false,"given":"Kevin","family":"Ros","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8071-7302","authenticated-orcid":false,"given":"Kedar","family":"Takwane","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5278-6012","authenticated-orcid":false,"given":"Ashwin","family":"Patil","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5875-7309","authenticated-orcid":false,"given":"Rakshana","family":"Jayaprakash","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6434-3702","authenticated-orcid":false,"given":"ChengXiang","family":"Zhai","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(00)00047-5"},{"volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit. \" O'Reilly Media","author":"Bird Steven","key":"e_1_3_2_1_3_1","unstructured":"Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python: analyzing text with the natural language toolkit. \" O'Reilly Media, Inc.\"."},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_5_1","unstructured":"Maciej Ceg?owski. 20224. Welcome to Pinboard! Social Bookmarking for Introverts. http:\/\/web.archive.org\/web\/20240201221915\/https:\/\/pinboard.in\/"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. https:\/\/doi.org\/10.48550\/ARXIV.2210.11416","DOI":"10.48550\/ARXIV.2210.11416"},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2005.93"},{"key":"e_1_3_2_1_9_1","unstructured":"Wang Chujiang et al. 2024. Markdown Editor React. https:\/\/uiwjs.github.io\/react-md-editor\/"},{"key":"e_1_3_2_1_10_1","unstructured":"Hugging Face. 2024. vicuna-7b-v1.5. https:\/\/huggingface.co\/lmsys\/vicuna-7b-v1.5"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Maarten Grootendorst. 2020. KeyBERT: Minimal keyword extraction with BERT. https:\/\/doi.org\/10.5281\/zenodo.4461265","DOI":"10.5281\/zenodo.4461265"},{"key":"e_1_3_2_1_12_1","volume-title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794","author":"Grootendorst Maarten","year":"2022","unstructured":"Maarten Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794 (2022)."},{"key":"e_1_3_2_1_13_1","unstructured":"Maarten Grootendorst. 2024. KeyLLM. https:\/\/maartengr.github.io\/KeyBERT\/guides\/keyllm.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_16_1","volume-title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. arXiv preprint arXiv:2306.00978","author":"Lin Ji","year":"2023","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Xingyu Dang, and Song Han. 2023. AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. arXiv preprint arXiv:2306.00978 (2023)."},{"key":"e_1_3_2_1_17_1","unstructured":"Steven Loria et al. 2018. textblob Documentation. Release 0.15 Vol. 2 8 (2018) 269."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357242"},{"key":"e_1_3_2_1_19_1","unstructured":"Notion. 2024. Notion. http:\/\/web.archive.org\/web\/20240207064918\/https:\/\/www.notion.so\/"},{"key":"e_1_3_2_1_20_1","unstructured":"Obsidian. 2024. Obsidian. http:\/\/web.archive.org\/web\/20240206011737\/https:\/\/obsidian.md\/"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445618"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545696"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609620"},{"key":"e_1_3_2_1_24_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_26_1","volume-title":"The CDL: An Online Platform for Creating Community-based Digital Libraries. In Companion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing. 372--375","author":"Ros Kevin","year":"2023","unstructured":"Kevin Ros and ChengXiang Zhai. 2023. The CDL: An Online Platform for Creating Community-based Digital Libraries. In Companion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing. 372--375."},{"key":"e_1_3_2_1_27_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems , Vol. 30 (2017)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462790"},{"key":"e_1_3_2_1_30_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arXiv preprint arXiv:2306.05685 (2023)."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Washington DC USA","acronym":"SIGIR 2024"},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657681","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:43:44Z","timestamp":1755841424000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657681"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":30,"alternative-id":["10.1145\/3626772.3657681","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657681","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}