{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:41:09Z","timestamp":1781887269264,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613905.3650798","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:15:21Z","timestamp":1715415321000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Automatic Histograms: Leveraging Language Models for Text Dataset Exploration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3572-6234","authenticated-orcid":false,"given":"Emily","family":"Reif","sequence":"first","affiliation":[{"name":"Google Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7716-7245","authenticated-orcid":false,"given":"Crystal","family":"Qian","sequence":"additional","affiliation":[{"name":"Google Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8105-6998","authenticated-orcid":false,"given":"James","family":"Wexler","sequence":"additional","affiliation":[{"name":"Google Research, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0291-6026","authenticated-orcid":false,"given":"Minsuk","family":"Kahng","sequence":"additional","affiliation":[{"name":"People + AI Research (PAIR), Google, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","unstructured":"[n. d.]. Data Quality for AI. https:\/\/www.ibm.com\/products\/dqaiapi"},{"key":"e_1_3_3_3_2_1","unstructured":"[n. d.]. Introducing the Data Measurements Tool: an Interactive Tool for Looking at Datasets. https:\/\/huggingface.co\/blog\/data-measurements-tool"},{"key":"e_1_3_3_3_3_1","unstructured":"[n. d.]. Know Your Data. https:\/\/knowyourdata.withgoogle.com\/"},{"key":"e_1_3_3_3_4_1","unstructured":"[n. d.]. Lilac: better data better AI. https:\/\/lilacml.com\/"},{"key":"e_1_3_3_3_5_1","unstructured":"[n. d.]. Using machine learning to reduce toxicity online. https:\/\/perspectiveapi.com\/"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFVIS.2005.1532136"},{"key":"e_1_3_3_3_7_1","volume-title":"Large Scale Qualitative Evaluation of Generative Image Model Outputs. arXiv preprint arXiv:2301.04518","author":"Assogba Yannick","year":"2023","unstructured":"Yannick Assogba, Adam Pearce, and Madison Elliott. 2023. Large Scale Qualitative Evaluation of Generative Image Model Outputs. arXiv preprint arXiv:2301.04518 (2023). https:\/\/arxiv.org\/abs\/2301.04518"},{"key":"e_1_3_3_3_8_1","volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit. O\u2019Reilly Media","author":"Bird Steven","unstructured":"Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python: analyzing text with the natural language toolkit. O\u2019Reilly Media, Inc."},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944937"},{"key":"e_1_3_3_3_10_1","volume-title":"arXiv preprint arXiv:2301.04528","author":"Brath Richard","year":"2023","unstructured":"Richard Brath, Daniel Keim, Johannes Knittel, Shimei Pan, Pia Sommerauer, and Hendrik Strobelt. 2023. arXiv preprint arXiv:2301.04528 (2023)."},{"key":"e_1_3_3_3_11_1","volume-title":"Using thematic analysis in psychology. Qualitative research in psychology 3, 2","author":"Braun Virginia","year":"2006","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology 3, 2 (2006), 77\u2013101."},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.212"},{"key":"e_1_3_3_3_13_1","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung\u00a0Won Chung Charles Sutton Sebastian Gehrmann Parker Schuh Kensen Shi Sasha Tsvyashchenko Joshua Maynez Abhishek Rao Parker Barnes Yi Tay Noam Shazeer Vinodkumar Prabhakaran Emily Reif Nan Du Ben Hutchinson Reiner Pope James Bradbury Jacob Austin Michael Isard Guy Gur-Ari Pengcheng Yin Toju Duke Anselm Levskaya Sanjay Ghemawat Sunipa Dev Henryk Michalewski Xavier Garcia Vedant Misra Kevin Robinson Liam Fedus Denny Zhou Daphne Ippolito David Luan Hyeontaek Lim Barret Zoph Alexander Spiridonov Ryan Sepassi David Dohan Shivani Agrawal Mark Omernick Andrew\u00a0M. Dai Thanumalayan\u00a0Sankaranarayana Pillai Marie Pellat Aitor Lewkowycz Erica Moreira Rewon Child Oleksandr Polozov Katherine Lee Zongwei Zhou Xuezhi Wang Brennan Saeta Mark Diaz Orhan Firat Michele Catasta Jason Wei Kathy Meier-Hellstern Douglas Eck Jeff Dean Slav Petrov and Noah Fiedel. 2022. PaLM: Scaling Language Modeling with Pathways. arxiv:2204.02311\u00a0[cs.CL]"},{"key":"e_1_3_3_3_14_1","unstructured":"Mark Diaz Sunipa Dev Emily Reif Emily Denton and Vinodkumar Prabhakaran. 2023. Developing A Conceptual Framework for Analyzing People in Unstructured Data. In Socially Responsible Language Modelling Research. https:\/\/openreview.net\/forum?id=QSPHfgw5fp"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"crossref","unstructured":"Jesse Dodge Ana Marasovic Gabriel Ilharco Dirk Groeneveld Margaret Mitchell and Matt Gardner. 2021. Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:237568724","DOI":"10.18653\/v1\/2021.emnlp-main.98"},{"key":"e_1_3_3_3_16_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=RvfPnOkPV4","author":"Elazar Yanai","year":"2024","unstructured":"Yanai Elazar, Akshita Bhagia, Ian\u00a0Helgi Magnusson, Abhilasha Ravichander, Dustin Schwenk, Alane Suhr, Evan\u00a0Pete Walsh, Dirk Groeneveld, Luca Soldaini, Sameer Singh, Hannaneh Hajishirzi, Noah\u00a0A. Smith, and Jesse Dodge. 2024. What\u2019s In My Big Data?. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=RvfPnOkPV4"},{"key":"e_1_3_3_3_17_1","volume-title":"Theory and applications of ontology: computer applications","author":"Fellbaum Christiane","unstructured":"Christiane Fellbaum. 2010. WordNet. In Theory and applications of ontology: computer applications. Springer, 231\u2013243."},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1613\/JAIR.1.13715"},{"key":"e_1_3_3_3_20_1","volume-title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794","author":"Grootendorst R.","year":"2022","unstructured":"Maarten\u00a0R. Grootendorst. 2022. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794 (2022)."},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACIFICVIS.2015.7156366"},{"key":"e_1_3_3_3_22_1","volume-title":"Evaluation of Synthetic Datasets for Conversational Recommender Systems. arXiv preprint arXiv:2212.08167","author":"Lara Harsh","year":"2022","unstructured":"Harsh Lara and Manoj\u00a0Kumar Tiwari. 2022. Evaluation of Synthetic Datasets for Conversational Recommender Systems. arXiv preprint arXiv:2212.08167 (2022). https:\/\/arxiv.org\/abs\/2212.08167"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533231"},{"key":"e_1_3_3_3_25_1","volume-title":"Understanding the Dataset Practitioners Behind Large Language Model Development. Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems.","author":"Qian Crystal","year":"2024","unstructured":"Crystal Qian, Emily Reif, and Minsuk Kahng. 2024. Understanding the Dataset Practitioners Behind Large Language Model Development. Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems."},{"key":"e_1_3_3_3_26_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a032. Curran Associates","author":"Reif Emily","year":"2019","unstructured":"Emily Reif, Ann Yuan, Martin Wattenberg, Fernanda\u00a0B Viegas, Andy Coenen, Adam Pearce, and Been Kim. 2019. Visualizing and Measuring the Geometry of BERT. In Advances in Neural Information Processing Systems, Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/159c1ffe5b61b41b3c4d8f4c2150f6c4-Paper.pdf"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.657"},{"key":"e_1_3_3_3_29_1","volume-title":"Topic Modelling Meets Deep Neural Networks: A Survey. In International Joint Conference on Artificial Intelligence. https:\/\/www.ijcai.org\/proceedings\/2021\/0638","author":"Zhao He","year":"2021","unstructured":"He Zhao, Dinh\u00a0Q. Phung, Viet Huynh, Yuan Jin, Lan Du, and Wray\u00a0L. Buntine. 2021. Topic Modelling Meets Deep Neural Networks: A Survey. In International Joint Conference on Artificial Intelligence. https:\/\/www.ijcai.org\/proceedings\/2021\/0638.pdf"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.01.026"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Extended Abstracts of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613905.3650798","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613905.3650798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:17Z","timestamp":1750290257000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613905.3650798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":30,"alternative-id":["10.1145\/3613905.3650798","10.1145\/3613905"],"URL":"https:\/\/doi.org\/10.1145\/3613905.3650798","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}