{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T10:37:17Z","timestamp":1777027037444,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Translation"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s10590-020-09254-w","type":"journal-article","created":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T01:44:29Z","timestamp":1612835069000},"page":"305-323","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Investigating alignment interpretability for low-resource NMT"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0134-6719","authenticated-orcid":false,"given":"Marcely Zanon","family":"Boito","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aline","family":"Villavicencio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Besacier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,6]]},"reference":[{"key":"9254_CR1","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.procs.2016.04.023","volume":"81","author":"G Adda","year":"2016","unstructured":"Adda G, St\u00fcker S, Adda-Decker M, Ambouroue O, Besacier L, Blachon D, Bonneau-Maynard H, Godard P, Hamlaoui F, Idiatov D, Kouarata GN, Lamel L, Makasso EM, Rialland A, de Velde MV, Yvon F, Zerbian S (2016) Breaking the unwritten language barrier: the BULB project. Procedia Comput Sci 81:8\u201314","journal-title":"Procedia Comput Sci"},{"key":"9254_CR2","doi-asserted-by":"publisher","unstructured":"Anastasopoulos A, Chiang D (2017) A case study on using speech-to-translation alignments for language documentation. In: Proceedings of the 2nd workshop on the use of computational methods in the study of endangered languages, pp. 170\u2013178. Association for Computational Linguistics, Honolulu . https:\/\/doi.org\/10.18653\/v1\/W17-0123","DOI":"10.18653\/v1\/W17-0123"},{"key":"9254_CR3","volume-title":"The Cambridge handbook of endangered languages","author":"PK Austin","year":"2011","unstructured":"Austin PK, Sallabank J (2011) The Cambridge handbook of endangered languages. Cambridge University Press, Cambridge"},{"key":"9254_CR4","volume-title":"Endangered languages","author":"PK Austin","year":"2013","unstructured":"Austin PK, Sallabank J (2013) Endangered languages. Taylor & Francis, Abingdon"},{"key":"9254_CR5","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural Machine translation by jointly learning to align and translate. In: ICLR 2015, pp. 3104\u20133112. San Diego, CA"},{"key":"9254_CR6","doi-asserted-by":"crossref","unstructured":"Bartels C, Wang W, Mitra V, Richey, C, Kathol A, Vergyri D, Bratt H, Hung C (2016) Toward human-assisted lexical unit discovery without text resources. In: Spoken language technology workshop (SLT), 2016 IEEE, pp. 64\u201370. IEEE","DOI":"10.1109\/SLT.2016.7846246"},{"key":"9254_CR7","unstructured":"B\u00e9rard A, Pietquin O, Servan C, Besacier L (2016) Listen and translate: a proof of concept for end-to-end speech-to-text translation. In: NIPS workshop on end-to-end learning for speech and audio processing"},{"key":"9254_CR8","doi-asserted-by":"crossref","unstructured":"Besacier L, Zhou B, Gao, Y (2006) Towards speech translation of non written languages. In: Spoken Language Technology Workshop, 2006. IEEE, pp. 222\u2013225. IEEE","DOI":"10.1109\/SLT.2006.326795"},{"key":"9254_CR9","doi-asserted-by":"crossref","unstructured":"Boito MZ, B\u00e9rard A, Villavicencio A, Besacier L (2017) Unwritten languages demand attention too! word discovery with encoder-decoder models. In: 2017 IEEE automatic speech recognition and understanding workshop (ASRU), pp. 458\u2013465. IEEE","DOI":"10.1109\/ASRU.2017.8268972"},{"key":"9254_CR10","doi-asserted-by":"publisher","unstructured":"Boito MZ, Villavicencio A, Besacier L (2019) Empirical evaluation of sequence-to-sequence models for word discovery in low-resource settings. In: Proceedings of interspeech 2019, pp. 2688\u20132692 . https:\/\/doi.org\/10.21437\/Interspeech.2019-2029","DOI":"10.21437\/Interspeech.2019-2029"},{"key":"9254_CR11","unstructured":"Chorowski JK, Bahdanau D, Serdyuk D, Cho K, Bengio Y (2015) Attention-based models for speech recognition. In: Advances in neural information processing systems, pp. 577\u2013585"},{"key":"9254_CR12","doi-asserted-by":"crossref","unstructured":"Dunbar E, Cao XN, Benjumea J, Karadayi J, Bernard M, Besacier L, Anguera X, Dupoux E (2017) The zero resource speech challenge 2017. In: 2017 IEEE automatic speech recognition and understanding workshop (ASRU). IEEE, pp. 323\u2013330","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"9254_CR13","doi-asserted-by":"crossref","unstructured":"Duong L, Anastasopoulos A, Chiang D, Bird S, Cohn T (2016) An attentional model for speech translation without transcription. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies, pp. 949\u2013959","DOI":"10.18653\/v1\/N16-1109"},{"key":"9254_CR14","unstructured":"Dyer C, Chahuneau V, Smith NA (2013) A simple, fast, and effective reparameterization of ibm model 2. In: Proceedings of the 2013 conference of the North American chapter of the association for computational linguistics: human language technologies, pp. 644\u2013648"},{"key":"9254_CR15","doi-asserted-by":"publisher","unstructured":"Elbayad M, Besacier L, Verbeek J (2018) Pervasive attention: 2D convolutional neural networks for sequence-to-sequence prediction. In: Proceedings of the 22nd conference on computational natural language learning, pp. 97\u2013107. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/K18-1010","DOI":"10.18653\/v1\/K18-1010"},{"key":"9254_CR16","doi-asserted-by":"publisher","unstructured":"Garg S, Peitz S, Nallasamy U, Paulik M (2019) Jointly learning to align and translate with transformer models. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp. 4453\u20134462. Association for Computational Linguistics, Hong Kong, China. https:\/\/doi.org\/10.18653\/v1\/D19-1453","DOI":"10.18653\/v1\/D19-1453"},{"key":"9254_CR17","unstructured":"Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN (2017) Convolutional sequence to sequence learning. In: Proceedings of the 34th international conference on machine learning, vol 70, pp 1243\u20131252. JMLR. org"},{"key":"9254_CR18","unstructured":"Ghader H, Monz C (2017) What does attention in neural machine translation pay attention to? In: Proceedings of the eighth international joint conference on natural language processing (vol 1: Long Papers), pp. 30\u201339. Asian Federation of Natural Language Processing, Taipei, Taiwan . https:\/\/www.aclweb.org\/anthology\/I17-1004"},{"key":"9254_CR19","doi-asserted-by":"crossref","unstructured":"Godard P, Adda G, Adda-Decker M, Allauzen A, Besacier L, Bonneau-Maynard H, Kouarata GN, L\u00f6ser K, Rialland A, Yvon F (2016) Preliminary experiments on unsupervised word discovery in mboshi. In: Proceedings of interspeech","DOI":"10.21437\/Interspeech.2016-886"},{"key":"9254_CR20","unstructured":"Godard P, Adda G, Adda-Decker M, Benjumea J, Besacier L, Cooper-Leavitt J, Kouarata G, LamelL, Maynard H, M\u00fcller, M, Rialland A, St\u00fcker S, Yvon F, Boito MZ (2018) A very low resource language speech corpus for computational language documentation experiments. In: LREC. EuropeanLanguage Resources Association (ELRA)"},{"key":"9254_CR21","unstructured":"Godard P, Besacier L, Yvon F (2019) Controlling utterance length in nmt-based word segmentation with attention. In: 12th International workshop on spoken language translation (IWSLT)"},{"key":"9254_CR22","doi-asserted-by":"crossref","unstructured":"Godard P, Zanon\u00a0Boito M, OndelL, Berard A, Yvon F, Villavicencio A, Besacier L (2018) Unsupervised word segmentation from speech with attention. In: Interspeech","DOI":"10.21437\/Interspeech.2018-1308"},{"key":"9254_CR23","doi-asserted-by":"crossref","unstructured":"Goldwater S, Griffiths TL, Johnson M (2006) Contextual dependencies in unsupervised word segmentation. In: Proceedings of international conference on computational linguistics, pp. 673\u2013680. Sydney, Australia","DOI":"10.3115\/1220175.1220260"},{"issue":"1","key":"9254_CR24","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cognition.2009.03.008","volume":"112","author":"S Goldwater","year":"2009","unstructured":"Goldwater S, Griffiths TL, Johnson M (2009) A Bayesian framework for word segmentation: exploring the effects of context. Cognition 112(1):21\u201354","journal-title":"Cognition"},{"key":"9254_CR25","unstructured":"Goldwater SJ (2007) Nonparametric Bayesian models of lexical acquisition. Ph.D. thesis, Citeseer"},{"key":"9254_CR26","doi-asserted-by":"publisher","unstructured":"Jain S, Wallace BC (2019) Attention is not explanation. In: Proceedings of the 2019 conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies, vol 1 (Long and Short Papers), pp. 3543\u20133556. Association for Computational Linguistics, Minneapolis, Minnesota . https:\/\/doi.org\/10.18653\/v1\/N19-1357","DOI":"10.18653\/v1\/N19-1357"},{"key":"9254_CR27","doi-asserted-by":"crossref","unstructured":"Johnson M, Goldwater S (2009) Improving nonparameteric Bayesian inference: experiments on unsupervised word segmentation with adaptor grammars. In: Proceedings of NAACL-HLT, pp. 317\u2013325. Association for Computational Linguistics","DOI":"10.3115\/1620754.1620800"},{"key":"9254_CR28","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1162\/tacl_a_00065","volume":"5","author":"M Johnson","year":"2017","unstructured":"Johnson M, Schuster M, Le QV, Krikun M, Wu Y, Chen Z, Thorat N, Vi\u00e9gas F, Wattenberg M, Corrado G et al (2017) Google\u2019s multilingual neural machine translation system: enabling zero-shot translation. Trans Assoc Comput Linguist 5:339\u2013351","journal-title":"Trans Assoc Comput Linguist"},{"key":"9254_CR29","unstructured":"Lignos C, Yang C (2010) Recession segmentation: simpler online word segmentation using limited resources. In: Proceedings of the fourteenth conference on computational natural language learning, pp. 88\u201397. Association for Computational Linguistics"},{"key":"9254_CR30","unstructured":"Lin Z, Feng M, dos Santos C, Yu M, Xiang B, Zhou B, Bengio Y (2017) A structured self-attentivesentence embedding. In: ICLR"},{"key":"9254_CR31","doi-asserted-by":"publisher","unstructured":"Luong T, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp. 1412\u20131421. Association for Computational Linguistics, Lisbon, Portugal. https:\/\/doi.org\/10.18653\/v1\/D15-1166","DOI":"10.18653\/v1\/D15-1166"},{"key":"9254_CR32","unstructured":"Michel P, Levy O, Neubig G (2019) Aresixteen heads really better than one? In: Advances in neural information processing systems, pp. 14014\u201314024"},{"key":"9254_CR33","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.procs.2016.04.033","volume":"81","author":"L Ondel","year":"2016","unstructured":"Ondel L, Burget L, \u010cernock\u1ef3 J (2016) Variational inference for acoustic unit discovery. Procedia Comput Sci 81:80\u201386","journal-title":"Procedia Comput Sci"},{"key":"9254_CR34","doi-asserted-by":"crossref","unstructured":"Ott M, Edunov S, Baevski A, Fan A, Gross S, Ng N, Grangier D, Auli M (2019) fairseq: a fast,extensible toolkit for sequence modeling. In: Proceedings of NAACL-HLT 2019: demonstrations","DOI":"10.18653\/v1\/N19-4009"},{"key":"9254_CR35","doi-asserted-by":"publisher","unstructured":"Serrano S, Smith NA (2019) Isattention interpretable? In: Proceedings of the 57th annual meeting of the Association for Computational Linguistics, pp. 2931\u20132951. Association for Computational Linguistics, Florence, Italy .https:\/\/doi.org\/10.18653\/v1\/P19-1282","DOI":"10.18653\/v1\/P19-1282"},{"key":"9254_CR36","doi-asserted-by":"crossref","unstructured":"Shen J, Pang R, Weiss RJ, Schuster M, Jaitly N, Yang Z, Chen Z, Zhang Y, Wang Y, Skerrv-Ryan R, et al (2018) Natural tts synthesis by conditioning wavenet on mel spectrogram predictions. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4779\u20134783","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"9254_CR37","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds) Advances in neural information processing systems 27, pp 3104\u20133112. Curran Associates, Inc. .http:\/\/papers.nips.cc\/paper\/5346-sequence-to-sequence-learning-with-neural-networks.pdf"},{"key":"9254_CR38","unstructured":"Vashishth S, Upadhyay S, Tomar GS, Faruqui M (2019) Attention interpretability across nlp tasks. arXiv preprint arXiv:1909.11218"},{"key":"9254_CR39","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, PolosukhinI (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"9254_CR40","doi-asserted-by":"publisher","unstructured":"Voita E, Talbot D, Moiseev F, Sennrich R, Titov I (2019) Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: Proceedings of the 57th annual meeting of the Association for Computational Linguistics, pp. 5797\u20135808. Association for Computational Linguistics, Florence, Italy .https:\/\/doi.org\/10.18653\/v1\/P19-1580","DOI":"10.18653\/v1\/P19-1580"},{"key":"9254_CR41","doi-asserted-by":"crossref","unstructured":"Wang Y, Skerry-Ryan R, Stanton D, Wu Y, Weiss RJ, Jaitly N, Yang Z, Xiao Y, Chen Z, Bengio S, et al (2017) Tacotron: towards end-to-end speech synthesis. Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017","DOI":"10.21437\/Interspeech.2017-1452"},{"issue":"8","key":"9254_CR42","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","volume":"11","author":"S Watanabe","year":"2017","unstructured":"Watanabe S, Hori T, Kim S, Hershey JR, Hayashi T (2017) Hybrid ctc\/attention architecture for end-to-end speech recognition. IEEE J Sel Top Signal Process 11(8):1240\u20131253","journal-title":"IEEE J Sel Top Signal Process"},{"key":"9254_CR43","doi-asserted-by":"publisher","unstructured":"Wiegreffe S, Pinter Y (2019) Attention is not not explanation. In: Proceedings of the 2019 conference on empirical methods in natural language Processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp. 11\u201320. Association for Computational Linguistics, Hong Kong, China. https:\/\/doi.org\/10.18653\/v1\/D19-1002","DOI":"10.18653\/v1\/D19-1002"},{"key":"9254_CR44","unstructured":"Zenkel T, Wuebker J, DeNero J (2019) Adding interpretable attention to neural translation models improves word alignment. arXiv preprint arXiv:1901.11359"}],"container-title":["Machine Translation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-020-09254-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10590-020-09254-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-020-09254-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:12:41Z","timestamp":1614251561000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10590-020-09254-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["9254"],"URL":"https:\/\/doi.org\/10.1007\/s10590-020-09254-w","relation":{},"ISSN":["0922-6567","1573-0573"],"issn-type":[{"value":"0922-6567","type":"print"},{"value":"1573-0573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]},"assertion":[{"value":"24 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}