{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:45:23Z","timestamp":1742931923007,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031084201"},{"type":"electronic","value":"9783031084218"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-08421-8_17","type":"book-chapter","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T21:02:38Z","timestamp":1658178158000},"page":"245-260","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Punctuation Restoration in\u00a0Spoken Italian Transcripts with\u00a0Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0736-5411","authenticated-orcid":false,"given":"Alessio","family":"Miaschi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0232-8881","authenticated-orcid":false,"given":"Andrea Amelio","family":"Ravelli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3454-9387","authenticated-orcid":false,"given":"Felice","family":"Dell\u2019Orletta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","unstructured":"Alam, T., Khan, A., Alam, F.: Punctuation restoration using transformer models for high-and low-resource languages. In: Proceedings of the Sixth Workshop on Noisy User-Generated Text (W-NUT 2020), pp. 132\u2013142. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.wnut-1.18. https:\/\/aclanthology.org\/2020.wnut-1.18","DOI":"10.18653\/v1\/2020.wnut-1.18"},{"key":"17_CR2","unstructured":"Baroni, M., et al.: Introducing the La Repubblica Corpus: a large, annotated, TEI (XML)-compliant Corpus of Newspaper Italian. In: LREC (2004)"},{"issue":"3","key":"17_CR3","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s10579-009-9081-4","volume":"43","author":"M Baroni","year":"2009","unstructured":"Baroni, M., Bernardini, S., Ferraresi, A., Zanchetta, E.: The WaCky wide web: a collection of very large linguistically processed web-crawled corpora. Lang. Resour. Eval. 43(3), 209\u2013226 (2009). https:\/\/doi.org\/10.1007\/s10579-009-9081-4","journal-title":"Lang. Resour. Eval."},{"key":"17_CR4","unstructured":"Bosco, C., Simonetta, M., Maria, S.: Converting Italian treebanks: towards an Italian stanford dependency treebank. In: 7th Linguistic Annotation Workshop and Interoperability with Discourse, pp. 61\u201369. The Association for Computational Linguistics (2013)"},{"key":"17_CR5","unstructured":"Bosco, C., Simonetta, M., Maria, S., et al.: Harmonization and merging of two Italian dependency treebanks. In: LREC 2012 Workshop on Language Resource Merging, pp. 23\u201330. ELRA (2012)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Che, X., Luo, S., Yang, H., Meinel, C.: Sentence boundary detection based on parallel lexical and acoustic models. In: INTERSPEECH, pp. 2528\u20132532 (2016)","DOI":"10.21437\/Interspeech.2016-257"},{"key":"17_CR7","unstructured":"Christensen, H., Gotoh, Y., Renals, S.: Punctuation annotation using statistical prosody models (2001)"},{"key":"17_CR8","unstructured":"De Mauro, T.: Il Nuovo vocabolario di base della lingua italiana. In: Guida all\u2019uso delle parole. Editori Riuniti (1980)"},{"key":"17_CR9","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota (Long and Short Papers), vol. 1, pp. 4171\u20134186. Association for Computational Linguistics, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"17_CR10","unstructured":"Erjavec, T., et al.: Multilingual comparable corpora of parliamentary debates ParlaMint 2.1 (2021). http:\/\/hdl.handle.net\/11356\/1432, Slovenian language resource repository CLARIN.SI"},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Fang, M., Zhao, H., Song, X., Wang, X., Huang, S.: Using bidirectional LSTM with BERT for Chinese punctuation prediction. In: 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), pp. 1\u20135 (2019). https:\/\/doi.org\/10.1109\/ICSIDP47821.2019.9172986","DOI":"10.1109\/ICSIDP47821.2019.9172986"},{"key":"17_CR12","unstructured":"Gotoh, Y., Renals, S.: Sentence boundary detection in broadcast speech transcripts. In: Automatic Speech Recognition: Challenges for the New Millenium ISCA Tutorial and Research Workshop (ITRW), ASR 2000 (2000)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Gravano, A., Jansche, M., Bacchiani, M.: Restoring punctuation and capitalization in transcribed speech. In: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4741\u20134744. IEEE (2009)","DOI":"10.1109\/ICASSP.2009.4960690"},{"issue":"4","key":"17_CR14","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1016\/S0167-6393(03)00049-9","volume":"41","author":"JH Kim","year":"2003","unstructured":"Kim, J.H., Woodland, P.C.: A combined punctuation generation and speech recognition system and its performance enhancement using prosody. Speech Commun. 41(4), 563\u2013577 (2003)","journal-title":"Speech Commun."},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Kim, S.: Deep recurrent neural networks with layer-wise multi-head attentions for punctuation restoration. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 7280\u20137284. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682418"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Klejch, O., Bell, P., Renals, S.: Punctuated transcription of multi-genre broadcasts using acoustic and lexical approaches. In: 2016 IEEE Spoken Language Technology Workshop (SLT), pp. 433\u2013440. IEEE (2016)","DOI":"10.1109\/SLT.2016.7846300"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Klejch, O., Bell, P., Renals, S.: Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5700\u20135704. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953248"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Levy, T., Silber-Varod, V., Moyal, A.: The effect of pitch, intensity and pause duration in punctuation detection. In: 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, pp. 1\u20134. IEEE (2012)","DOI":"10.1109\/EEEI.2012.6376934"},{"key":"17_CR19","unstructured":"Lison, P., Tiedemann, J.: OpenSubtitles 2016: extracting large parallel corpora from movie and TV subtitles (2016)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Makhija, K., Ho, T.N., Chng, E.S.: Transfer learning for punctuation prediction. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 268\u2013273. IEEE (2019)","DOI":"10.1109\/APSIPAASC47483.2019.9023200"},{"key":"17_CR21","unstructured":"Miaschi, A., Ravelli, A.A., Dell\u2019Orletta, F.: Evaluating transformer models for punctuation restoration in Italian. In: Proceedings of the Fifth Workshop on Natural Language for Artificial Intelligence (NL4AI 2021). CEUR Workshop Proceedings, vol. 3015. CEUR-WS.org (2021)"},{"key":"17_CR22","unstructured":"Nagy, A., Bial, B., \u00c1cs, J.: Automatic punctuation restoration with BERT models. arXiv preprint arXiv:2101.07343 (2021)"},{"key":"17_CR23","unstructured":"Nencioni, G.: Parlato-parlato, parlato-scritto, parlato-recitato. Strumenti critici 29 (1976)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Qi, P., Zhang, Y., Zhang, Y., Bolton, J., Manning, C.D.: Stanza: a python natural language processing toolkit for many human languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 101\u2013108 (2020)","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"17_CR25","unstructured":"Sabatini, F.: La comunicazione orale, scritta e trasmessa. In: Boccafurni, A.M., Serromani, S. (eds.) Educazione linguistica nella scuola superiore: sei argomenti per un curricolo, pp. 105\u2013127 (1982)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Salesky, E., et al.: Multilingual TEDx corpus for speech recognition and translation. In: Proceedings of INTERSPEECH (2021)","DOI":"10.21437\/Interspeech.2021-11"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Salesky, E., et al.: The multilingual TEDx corpus for speech recognition and translation. arXiv:2102.01757 (2021)","DOI":"10.21437\/Interspeech.2021-11"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862 (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Stolcke, A., et al.: Automatic detection of sentence boundaries and disfluencies based on recognized words. In: ICSLP, vol. 2, pp. 2247\u20132250. Citeseer (1998)","DOI":"10.21437\/ICSLP.1998-486"},{"key":"17_CR30","unstructured":"Su\u00e1rez, P.J.O., Sagot, B., Romary, L.: Asynchronous pipeline for processing huge corpora on medium to low resource infrastructures. In: Challenges in the Management of Large Corpora (CMLC-7), p. 9 (2019)"},{"key":"17_CR31","unstructured":"Tiedemann, J., Nygaard, L.: The OPUS corpus-parallel and free. Citeseer (2004). http:\/\/logos.uio.no\/opus"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Tilk, O., Alum\u00e4e, T.: LSTM for punctuation restoration in speech transcripts. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-240"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Tilk, O., Alum\u00e4e, T.: Bidirectional recurrent neural network with attention mechanism for punctuation restoration. In: INTERSPEECH, pp. 3047\u20133051 (2016)","DOI":"10.21437\/Interspeech.2016-1517"},{"key":"17_CR34","doi-asserted-by":"publisher","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, October 2020. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Yi, J., Tao, J.: Self-attention based model for punctuation prediction using word and speech embeddings. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 7270\u20137274. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682260"},{"key":"17_CR36","unstructured":"Yi, J., Tao, J., Bai, Y., Tian, Z., Fan, C.: Adversarial transfer learning for punctuation restoration. arXiv preprint arXiv:2004.00248 (2020)"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Yi, J., Tao, J., Wen, Z., Li, Y., et al.: Distilling knowledge from an ensemble of models for punctuation prediction. In: INTERSPEECH, pp. 2779\u20132783 (2017)","DOI":"10.21437\/Interspeech.2017-1079"}],"container-title":["Lecture Notes in Computer Science","AIxIA 2021 \u2013 Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08421-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T22:30:54Z","timestamp":1676154654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08421-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031084201","9783031084218"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08421-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIxIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aixia2021.disco.unimib.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"58","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"36","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}