{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T18:43:01Z","timestamp":1747680181208},"reference-count":48,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"vor","delay-in-days":247,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until after the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model.1<\/jats:p>","DOI":"10.1162\/tacl_a_00691","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:36:25Z","timestamp":1725456985000},"page":"1104-1121","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":1,"title":["Segmentation-Free Streaming Machine Translation"],"prefix":"10.1162","volume":"12","author":[{"given":"Javier","family":"Iranzo-S\u00e1nchez","sequence":"first","affiliation":[{"name":"Machine Learning and Language Processing, VRAIN, Universitat Polit\u00e8cnica de Val\u00e8ncia, Spain. jairsan@upv.es"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorge","family":"Iranzo-S\u00e1nchez","sequence":"additional","affiliation":[{"name":"Machine Learning and Language Processing, VRAIN, Universitat Polit\u00e8cnica de Val\u00e8ncia, Spain. jorirsan@upv.es"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adri\u00e0","family":"Gim\u00e9nez","sequence":"additional","affiliation":[{"name":"Departament d\u2019Inform\u00e0tica, Escola T\u00e8cnica Superior d\u2019Enginyeria, Universitat de Val\u00e8ncia, Spain. adria.gimenez@uv.es"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorge","family":"Civera","sequence":"additional","affiliation":[{"name":"Machine Learning and Language Processing, VRAIN, Universitat Polit\u00e8cnica de Val\u00e8ncia, Spain. jorcisai@upv.es"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfons","family":"Juan","sequence":"additional","affiliation":[{"name":"Machine Learning and Language Processing, VRAIN, Universitat Polit\u00e8cnica de Val\u00e8ncia, Spain. ajuanci@upv.es"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2024,9,4]]},"reference":[{"key":"2024090413343199700_bib1","first-page":"31","article-title":"Contextual handling in neural machine translation: Look behind, ahead and on both sides","volume-title":"Proceedings of the 21st Annual Conference of the European Association for Machine Translation","author":"Agrawal","year":"2018"},{"key":"2024090413343199700_bib2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.18653\/v1\/2022.iwslt-1.10","article-title":"Findings of the IWSLT 2022 evaluation campaign","volume-title":"Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)","author":"Anastasopoulos","year":"2022"},{"key":"2024090413343199700_bib3","doi-asserted-by":"publisher","first-page":"7919","DOI":"10.1109\/ICASSP40776.2020.9054585","article-title":"Re-translation strategies for long form, simultaneous, spoken language translation","volume-title":"2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4\u20138, 2020","author":"Arivazhagan","year":"2020"},{"key":"2024090413343199700_bib4","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.18653\/v1\/P19-1126","article-title":"Monotonic infinite lookback attention for simultaneous machine translation","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Arivazhagan","year":"2019"},{"key":"2024090413343199700_bib5","doi-asserted-by":"publisher","first-page":"220","DOI":"10.18653\/v1\/2020.iwslt-1.27","article-title":"Re-translation versus streaming for simultaneous translation","volume-title":"Proceedings of the 17th International Conference on Spoken Language Translation","author":"Arivazhagan","year":"2020"},{"key":"2024090413343199700_bib6","doi-asserted-by":"publisher","first-page":"52","DOI":"10.18653\/v1\/2021.iwslt-1.5","article-title":"Without further ado: Direct and simultaneous speech translation by AppTek in 2021","volume-title":"Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)","author":"Bahar","year":"2021"},{"key":"2024090413343199700_bib7","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/11816508_66","article-title":"Text segmentation criteria for statistical machine translation","volume-title":"Proceedings of Advances in Natural Language Processing, FinTAL","author":"Cettolo","year":"2006"},{"key":"2024090413343199700_bib8","first-page":"173","article-title":"Punctuation insertion for real-time spoken language translation","volume-title":"Proceedings of the 12th International Workshop on Spoken Language Translation: Papers","author":"Cho","year":"2015"},{"key":"2024090413343199700_bib9","first-page":"252","article-title":"Segmentation and punctuation prediction in speech language translation using a monolingual translation system","volume-title":"Proceedings of the 9th International Workshop on Spoken Language Translation: Papers","author":"Cho","year":"2012"},{"key":"2024090413343199700_bib10","doi-asserted-by":"publisher","first-page":"2645","DOI":"10.21437\/Interspeech.2017-1320","article-title":"NMT-based segmentation and punctuation insertion for real-time spoken language translation","volume-title":"Proceedings of Interspeech 2017","author":"Cho","year":"2017"},{"key":"2024090413343199700_bib11","article-title":"Can neural machine translation do simultaneous translation?","author":"Cho","year":"2016","journal-title":"arXiv preprint arXiv:1606.02012v1"},{"key":"2024090413343199700_bib12","doi-asserted-by":"publisher","first-page":"8440","DOI":"10.18653\/v1\/2020.acl-main.747","article-title":"Unsupervised cross-lingual representation learning at scale","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Conneau","year":"2020"},{"key":"2024090413343199700_bib13","doi-asserted-by":"publisher","first-page":"2978","DOI":"10.18653\/v1\/P19-1285","article-title":"Transformer-XL: Attentive language models beyond a fixed-length context","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Dai","year":"2019"},{"key":"2024090413343199700_bib14","first-page":"644","article-title":"A simple, fast, and effective reparameterization of IBM model 2","volume-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Dyer","year":"2013"},{"key":"2024090413343199700_bib15","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.21437\/Interspeech.2020-1241","article-title":"Efficient wait-k models for simultaneous machine translation","volume-title":"Proceedings of Interspeech 2020","author":"Elbayad","year":"2020"},{"key":"2024090413343199700_bib16","doi-asserted-by":"publisher","first-page":"6972","DOI":"10.18653\/v1\/2022.acl-long.480","article-title":"From simultaneous to streaming machine translation by leveraging streaming history","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sanchez","year":"2022"},{"key":"2024090413343199700_bib17","doi-asserted-by":"publisher","first-page":"664","DOI":"10.18653\/v1\/2021.findings-emnlp.58","article-title":"Stream-level latency evaluation for simultaneous machine translation","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","author":"Iranzo-S\u00e1nchez","year":"2021"},{"key":"2024090413343199700_bib18","doi-asserted-by":"publisher","first-page":"2599","DOI":"10.18653\/v1\/2020.emnlp-main.206","article-title":"Direct segmentation models for streaming speech translation","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Iranzo-S\u00e1nchez","year":"2020"},{"key":"2024090413343199700_bib19","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.neunet.2021.05.013","article-title":"Streaming cascade- based speech translation leveraged by a direct segmentation model","volume":"142","author":"Iranzo-S\u00e1nchez","year":"2021","journal-title":"Neural Networks"},{"key":"2024090413343199700_bib20","first-page":"1124","article-title":"Simultaneous neural machine translation with constituent label prediction","volume-title":"Proceedings of the Sixth Conference on Machine Translation","author":"Kano","year":"2021"},{"key":"2024090413343199700_bib21","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing","author":"Koehn","year":"2004"},{"key":"2024090413343199700_bib22","first-page":"79","article-title":"Europarl: A parallel corpus for statistical machine translation","volume-title":"Proceedings of Machine Translation Summit X: Papers","author":"Koehn","year":"2005"},{"key":"2024090413343199700_bib23","doi-asserted-by":"publisher","first-page":"2735","DOI":"10.21437\/Interspeech.2008-678","article-title":"Stream decoding for simultaneous spoken language translation","volume-title":"INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, September 22-26, 2008","author":"Kolss","year":"2008"},{"key":"2024090413343199700_bib24","doi-asserted-by":"publisher","first-page":"66","DOI":"10.18653\/v1\/D18-2012","article-title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Kudo","year":"2018"},{"key":"2024090413343199700_bib25","doi-asserted-by":"crossref","first-page":"7553","DOI":"10.1109\/ICASSP39728.2021.9413492","article-title":"Sentence boundary augmentation for neural machine translation robustness","volume-title":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Li","year":"2021"},{"key":"2024090413343199700_bib26","doi-asserted-by":"publisher","first-page":"39","DOI":"10.18653\/v1\/2021.emnlp-main.4","article-title":"Cross attention augmented transducer networks for simultaneous translation","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Liu","year":"2021"},{"key":"2024090413343199700_bib27","doi-asserted-by":"publisher","first-page":"3025","DOI":"10.18653\/v1\/P19-1289","article-title":"STACL: Simultaneous translation with implicit anticipation and controllable latency using prefix-to-prefix framework","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Ma","year":"2019"},{"key":"2024090413343199700_bib28","doi-asserted-by":"publisher","first-page":"3505","DOI":"10.18653\/v1\/2020.acl-main.321","article-title":"A simple and effective unified encoder for document-level machine translation","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Ma","year":"2020"},{"key":"2024090413343199700_bib29","article-title":"Monotonic multihead attention","volume-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","author":"Ma","year":"2020"},{"key":"2024090413343199700_bib30","article-title":"Evaluating machine translation output with automatic sentence segmentation","volume-title":"Proceedings of the Second International Workshop on Spoken Language Translation","author":"Matusov","year":"2005"},{"key":"2024090413343199700_bib31","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3115\/1073083.1073135","article-title":"Bleu: A method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"2024090413343199700_bib32","doi-asserted-by":"publisher","first-page":"186","DOI":"10.18653\/v1\/W18-6319","article-title":"A call for clarity in reporting BLEU scores","volume-title":"Proceedings of the Third Conference on Machine Translation: Research Papers","author":"Post","year":"2018"},{"key":"2024090413343199700_bib33","doi-asserted-by":"publisher","first-page":"751","DOI":"10.18653\/v1\/2021.emnlp-main.58","article-title":"Learning compact metrics for MT","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Amy","year":"2021"},{"key":"2024090413343199700_bib34","doi-asserted-by":"publisher","first-page":"51","DOI":"10.18653\/v1\/D19-6506","article-title":"Analysing concatenation approaches to document-level NMT in two different domains","volume-title":"Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)","author":"Scherrer","year":"2019"},{"key":"2024090413343199700_bib35","doi-asserted-by":"publisher","first-page":"228","DOI":"10.18653\/v1\/2020.iwslt-1.28","article-title":"Towards stream translation: Adaptive computation time for simultaneous machine translation","volume-title":"Proceedings of the 17th International Conference on Spoken Language Translation","author":"Schneider","year":"2020"},{"key":"2024090413343199700_bib36","article-title":"Simultaneous translation for unsegmented input: A sliding window approach","author":"Sen","year":"2022","journal-title":"arXiv preprint arXiv:2210.09754v1"},{"key":"2024090413343199700_bib37","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.21437\/ICSLP.1996-259","article-title":"Automatic linguistic segmentation of conversational speech","volume-title":"Proceedings of the Fourth International Conference on Spoken Language Processing","author":"Stolcke","year":"1996"},{"key":"2024090413343199700_bib38","doi-asserted-by":"publisher","DOI":"10.1075\/cilt.309.19tie","volume-title":"News from OPUS - A Collection of Multilingual Parallel Corpora with Tools and Interfaces","author":"Tiedemann","year":"2009"},{"key":"2024090413343199700_bib39","doi-asserted-by":"publisher","first-page":"82","DOI":"10.18653\/v1\/W17-4811","article-title":"Neural machine translation with extended context","volume-title":"Proceedings of the Third Workshop on Discourse in Machine Translation","author":"Tiedemann","year":"2017"},{"key":"2024090413343199700_bib40","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2024090413343199700_bib41","doi-asserted-by":"publisher","first-page":"237","DOI":"10.18653\/v1\/2020.iwslt-1.29","article-title":"Neural simultaneous speech translation using alignment-based chunking","volume-title":"Proceedings of the 17th International Conference on Spoken Language Translation","author":"Wilken","year":"2020"},{"key":"2024090413343199700_bib42","first-page":"123","article-title":"Dynamic masking for improved stability in online spoken language translation","volume-title":"Proceedings of the 14th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)","author":"Yao","year":"2020"},{"key":"2024090413343199700_bib43","doi-asserted-by":"publisher","first-page":"2566","DOI":"10.18653\/v1\/2021.acl-long.200","article-title":"Beyond sentence-level end-to-end speech translation: Context helps","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Zhang","year":"2021"},{"key":"2024090413343199700_bib44","doi-asserted-by":"publisher","first-page":"7862","DOI":"10.18653\/v1\/2022.acl-long.542","article-title":"Learning adaptive segmentation policy for end-to-end simultaneous translation","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhang","year":"2022"},{"key":"2024090413343199700_bib45","doi-asserted-by":"publisher","first-page":"2280","DOI":"10.18653\/v1\/2020.emnlp-main.178","article-title":"Learning adaptive segmentation policy for simultaneous translation","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Zhang","year":"2020"},{"key":"2024090413343199700_bib46","doi-asserted-by":"publisher","first-page":"2847","DOI":"10.18653\/v1\/2020.acl-main.254","article-title":"Simultaneous translation policies: From fixed to adaptive","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Zheng","year":"2020"},{"key":"2024090413343199700_bib47","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.18653\/v1\/D19-1144","article-title":"Speculative beam search for simultaneous translation","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Zheng","year":"2019"},{"key":"2024090413343199700_bib48","doi-asserted-by":"publisher","first-page":"3983","DOI":"10.24963\/ijcai.2020\/551","article-title":"Towards making the most of context in neural machine translation","volume-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","author":"Zheng","year":"2020"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00691\/2468656\/tacl_a_00691.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00691\/2468656\/tacl_a_00691.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:36:37Z","timestamp":1725456997000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00691\/124259\/Segmentation-Free-Streaming-Machine-Translation"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00691","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}