{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T09:36:36Z","timestamp":1710408996038},"reference-count":31,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,1,1]]},"DOI":"10.1587\/transinf.2021edp7081","type":"journal-article","created":{"date-parts":[[2021,12,31]],"date-time":"2021-12-31T22:24:21Z","timestamp":1640989461000},"page":"150-160","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Source Domain Generalization Using Domain Attributes for Recurrent Neural Network Language Models"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Naohiro","family":"TAWARA","sequence":"first","affiliation":[{"name":"NTT Communication Science Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"OGAWA","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoharu","family":"IWATA","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroto","family":"ASHIKAWA","sequence":"additional","affiliation":[{"name":"Department of Communications and Computer Engineering, Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsunori","family":"KOBAYASHI","sequence":"additional","affiliation":[{"name":"Department of Communications and Computer Engineering, Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"OGAWA","sequence":"additional","affiliation":[{"name":"Department of Communications and Computer Engineering, Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] X. Chen, T. Tan, X. Liu, P. Lanchantin, M. Wan, M.J.F. Gales, and P.C. Woodland, \u201cRecurrent neural network language model adaptation for multi-genre broadcast speech recognition,\u201d Proc. INTERSPEECH, pp.3511-3515, 2015. 10.21437\/interspeech.2015-696","DOI":"10.21437\/Interspeech.2015-696"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] T. Morioka, N. Tawara, T. Ogawa, A. Ogawa, T. Iwata, and T. Kobayashi, \u201cLanguage model domain adaptation via recurrent neural networks with domain-shared and domain-specific representations,\u201d Proc. ICASSP, pp.6084-6088, 2018. 10.1109\/icassp.2018.8462631","DOI":"10.1109\/ICASSP.2018.8462631"},{"key":"3","unstructured":"[3] J. Brousseau and S.A. Fox, \u201cDialect-dependent speech recognizers for Canadian and European French,\u201d Proc. ICSLP, pp.1003-1006, 1992."},{"key":"4","unstructured":"[4] R.C. Moore and W.D. Lewis, \u201cIntelligent selection of language model training data,\u201d Proc. ACL, pp.220-224, 2010."},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] R. Masumura, S. Hahm, and A. Ito, \u201cTraining a language model using webdata for large vocabulary Japanese spontaneous speech recognition,\u201d Proc. INTERSPEECH, pp.1465-1468, 2011. 10.21437\/interspeech.2011-258","DOI":"10.21437\/Interspeech.2011-258"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] Z. T\u00fcske, K. Irie, R. Schl\u00fcter, and H. Ney, \u201cInvestigation on log-linear interpolation of multi-domain neural network language model,\u201d Proc. ICASSP, pp.6005-6009, 2016. 10.1109\/icassp.2016.7472830","DOI":"10.1109\/ICASSP.2016.7472830"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] S. Deena, M. Hasan, M. Doulaty, O. Saz, and T. Hain, \u201cCombining feature and model-based adaptation of RNNLMs for multi-genre broadcast speech recognition,\u201d Proc. INTERSPEECH, pp.2343-2347, 2016. 10.21437\/interspeech.2016-480","DOI":"10.21437\/Interspeech.2016-480"},{"key":"8","unstructured":"[8] H. Daum\u00e9 III, \u201cFrustratingly easy domain adaptation,\u201d Proc. ACL, pp.256-263, 2007."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] J. Park, X. Liu, M.J.F. Gales, and P.C. Woodland, \u201cImproved neural network based language modelling and adaptation,\u201d Proc. INTERSPEECH, pp.1041-1044, 2010. 10.21437\/interspeech.2010-342","DOI":"10.21437\/Interspeech.2010-342"},{"key":"10","unstructured":"[10] K. Bousmalis, G. Trigeorgis, N. Silberman, D. Krishnan, and D. Erhan, \u201cDomain separation networks,\u201d Proc. NIPS, pp.343-351, 2016."},{"key":"11","unstructured":"[11] K. Young-Bum, S. Karl, and K. Dongchan, \u201cDomain attention with an ensemble of experts,\u201d Proc. ACL, pp.643-653, 2017. 10.18653\/v1\/p17-1060"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] K. Irie, S. Kumar, M. Nirschl, and H. Liao, \u201cRADMM: recurrent adaptive mixture model with applications to domain robust language modeling,\u201d Proc. ICASSP, pp.6079-6083, 2018. 10.1109\/icassp.2018.8461628","DOI":"10.1109\/ICASSP.2018.8461628"},{"key":"13","unstructured":"[13] J. Zhang, X. Wu, A. Way, and Q. Liu, \u201cFast gated neural domain adaptation: Language model as a case study,\u201d Proc. COLING, pp.1386-1397, 2016."},{"key":"14","unstructured":"[14] E. Garmash and C. Monz, \u201cEnsemble learning for multi-source neural machine translation,\u201d Proc. COLING, pp.1409-1418, 2016."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] S. Li and C. Zong, \u201cMulti-domain sentiment classification,\u201d Proc. ACL: HLT, Short Papers, pp.257-260, 2008. 10.3115\/1557690.1557765","DOI":"10.3115\/1557690.1557765"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] J. Guo, D. Shah, and R. Barzilay, \u201cMulti-source domain adaptation with mixture of experts,\u201d Proc. EMNLP, pp.4694-4703, 2018. 10.18653\/v1\/d18-1498","DOI":"10.18653\/v1\/D18-1498"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] R.A. Jacobs, M.I. Jordan, S.J. Nowlan, and G.E. Hinton, \u201cAdaptive mixtures of local experts,\u201d Neural Comput, vol.3, no.1, pp.79-87, 1991. 10.1162\/neco.1991.3.1.79","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"18","unstructured":"[18] G. Blanchard, G. Lee, and C. Scott, \u201cGeneralizing from several related classification tasks to a new unlabeled sample,\u201d Proc. NIPS, pp.2178-2186, 2011."},{"key":"19","unstructured":"[19] K. Muandet, D. Balduzzi, and B. Sch\u00f6lkopf, \u201cDomain generalization via invariant feature representation,\u201d Proc. ICML, pp.10-18, 2013."},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] C. Gan, T. Yang, and B. Gong, \u201cLearning attributes equals multi-source domain generalization,\u201d Proc. CVPR, pp.87-97, 2016. 10.1109\/cvpr.2016.17","DOI":"10.1109\/CVPR.2016.17"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] M. Ghifary, W.B. Kleijn, M. Zhang, and D. Balduzzi, \u201cDomain generalization for object recognition with multi-task autoencoders,\u201d Proc. ICCV, pp.2551-2559, 2015. 10.1109\/iccv.2015.293","DOI":"10.1109\/ICCV.2015.293"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] D. Li, Y. Yang, Y.-Z. Song, and T.M. Hospedales, \u201cDeeper, broader and artier domain generalization,\u201d Proc. ICCV, pp.5543-5551, 2017. 10.1109\/iccv.2017.591","DOI":"10.1109\/ICCV.2017.591"},{"key":"23","unstructured":"[23] Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky, \u201cDomain-adversarial training of neural networks,\u201d Journal of Machine Learning Research, vol.17, pp.59:1-59:35, 2016. 10.1007\/978-3-319-58347-1_10"},{"key":"24","unstructured":"[24] S. Shankar, V. Piratla, S. Chakrabarti, S. Chaudhuri, P. Jyothi, and S. Sarawagi, \u201cGeneralizing across domains via cross-gradient training,\u201d CoRR, vol.abs\/1804.10745, 2018."},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] S. Greenbaum and G. Nelson, \u201cThe international corpus of English (ICE) project,\u201d World Englishes, vol.15, no.1, pp.3-15, 1996. 10.1111\/j.1467-971x.1996.tb00088.x","DOI":"10.1111\/j.1467-971X.1996.tb00088.x"},{"key":"26","unstructured":"[26] S. Tokui, K. Oono, S. Hido, and J. Clayton, \u201cChainer: a next-generation open source framework for deep learning,\u201d Proc. workshop on LearningSys in NIPS, pp.1-6, 2015."},{"key":"27","unstructured":"[27] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014."},{"key":"28","unstructured":"[28] N. Ide and K. Suderman, \u201cThe American national corpus first release,\u201d Proc. LREC, pp.1681-1684, 2004."},{"key":"29","unstructured":"[29] G. Aston and L. Burnard, The BNC handbook: exploring the British National Corpus with SARA, Capstone, 1998."},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] H. Liao, E. McDermott, and A. Senior, \u201cLarge scale deep neural network acoustic modeling with semi-supervised training data for youtube video transcription,\u201d Proc. ASRU, pp.368-373, 2013. 10.1109\/asru.2013.6707758","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] M. Hentschel, M. Delcroix, A. Ogawa, T. Iwata, and T. Nakatani, \u201cFeature based domain adaptation for neural network language models with factorised hidden layers,\u201d IEICE Trans. Inf. & Syst., vol.102, no.3, pp.598-608, 2019. 10.1587\/transinf.2018edp7222","DOI":"10.1587\/transinf.2018EDP7222"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/1\/E105.D_2021EDP7081\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T04:11:10Z","timestamp":1641010270000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/1\/E105.D_2021EDP7081\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,1]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021edp7081","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,1]]},"article-number":"2021EDP7081"}}