{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T04:05:22Z","timestamp":1779509122381,"version":"3.53.1"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032026019","type":"print"},{"value":"9783032026026","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-02602-6_3","type":"book-chapter","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T08:33:50Z","timestamp":1755851630000},"page":"27-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Constructing Compact BPE Token DFAs"],"prefix":"10.1007","author":[{"given":"Martin","family":"Berglund","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Jonsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Willeke","family":"Martens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brink van der","family":"Merwe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,23]]},"reference":[{"issue":"6","key":"3_CR1","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1145\/360825.360855","volume":"18","author":"AV Aho","year":"1975","unstructured":"Aho, A.V., Corasick, M.J.: Efficient string matching: an aid to bibliographic search. Commun. ACM 18(6), 333\u2013340 (1975). https:\/\/doi.org\/10.1145\/360825.360855","journal-title":"Commun. ACM"},{"key":"3_CR2","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-031-71112-1_5","volume-title":"Implementation and Application of Automata","author":"M Berglund","year":"2024","unstructured":"Berglund, M., Martens, W., van der Merwe, B.: Constructing a BPE tokenization DFA. In: Fazekas, S.Z. (ed.) Implementation and Application of Automata, pp. 66\u201378. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-71112-1_5"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Berglund, M., van\u00a0der Merwe, B.: Formalizing BPE tokenization. In: 13th International Workshop on Non-Classical Models of Automata and Applications, NCMA 2023, Famagusta, Cyprus, 18\u201319 September 2023, pp. 16\u201327. Open Publishing Association (2023)","DOI":"10.4204\/EPTCS.388.4"},{"key":"3_CR4","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-031-82670-2_11","volume-title":"SOFSEM 2025: Theory and Practice of Computer Science","author":"P Bille","year":"2025","unstructured":"Bille, P., G\u00f8rtz, I.L., Pedersen, M.R.: Fast practical compression of deterministic finite automata. In: Kr\u00e1lovi\u010d, R., K\u016frkov\u00e1, V. (eds.) SOFSEM 2025: Theory and Practice of Computer Science, pp. 136\u2013150. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-82670-2_11"},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.tcs.2014.09.007","volume":"557","author":"H Bj\u00f6rklund","year":"2014","unstructured":"Bj\u00f6rklund, H., Bj\u00f6rklund, J., Zechner, N.: Compression of finite-state automata through failure transitions. Theor. Comput. Sci. 557, 87\u2013100 (2014)","journal-title":"Theor. Comput. Sci."},{"key":"3_CR6","unstructured":"HuggingFace: SmolLM 2 BPE dictionary (2024). https:\/\/huggingface.co\/HuggingFaceTB\/SmolLM2-1.7B\/blob\/main\/merges.txt. Accessed 22 Apr 2025"},{"key":"3_CR7","unstructured":"Kourie, D.G., Watson, B.W., Cleophas, L., Venter, F.: Failure deterministic finite automata. In: Holub, J., \u017d\u010f\u00e1rek, J. (eds.) Proceedings of the Prague Stringology Conference 2012, pp. 28\u201341. Czech Technical University in Prague, Czech Republic (2012)"},{"issue":"4","key":"3_CR8","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1145\/1151659.1159952","volume":"36","author":"S Kumar","year":"2006","unstructured":"Kumar, S., Dharmapurikar, S., Yu, F., Crowley, P., Turner, J.: Algorithms to accelerate multiple regular expressions matching for deep packet inspection. SIGCOMM Comput. Commun. Rev. 36(4), 339\u2013350 (2006). https:\/\/doi.org\/10.1145\/1151659.1159952","journal-title":"SIGCOMM Comput. Commun. Rev."},{"key":"3_CR9","unstructured":"Lindmark, V.: Analyzing the Effect of DFA Compression in Token DFAs. Master\u2019s thesis, Ume\u00e5 University, Department of Computing Science (2024)"},{"key":"3_CR10","unstructured":"Microsoft: Phi 4 BPE dictionary (2024). https:\/\/huggingface.co\/microsoft\/phi-4\/blob\/main\/merges.txt. Accessed 22 Apr 2025"},{"key":"3_CR11","unstructured":"OpenAI: GPT-2\/GPT-3 BPE dictionary (2019). https:\/\/huggingface.co\/openai-community\/gpt2\/blob\/main\/merges.txt. Accessed 22 Apr 2025"},{"key":"3_CR12","unstructured":"OpenAI: Whisper BPE dictionary (2024). https:\/\/huggingface.co\/openai\/whisper-large\/blob\/main\/merges.txt. Accessed 22 Apr 2025"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 1715\u20131725. Association for Computational Linguistics, Berlin (2016)","DOI":"10.18653\/v1\/P16-1162"}],"container-title":["Lecture Notes in Computer Science","Implementation and Application of Automata"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02602-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T03:23:46Z","timestamp":1779506626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02602-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,23]]},"ISBN":["9783032026019","9783032026026"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02602-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,23]]},"assertion":[{"value":"23 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CIAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Implementation and Application of Automata","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Palermo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wia2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ciaa2025.unipa.it","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}