{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T04:16:41Z","timestamp":1687061801348},"reference-count":51,"publisher":"Association for Natural Language Processing","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Natural Language Processing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.5715\/jnlp.30.456","type":"journal-article","created":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T22:14:09Z","timestamp":1686780849000},"page":"456-488","source":"Crossref","is-referenced-by-count":0,"title":["LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation"],"prefix":"10.5715","volume":"30","author":[{"given":"Thodsaporn","family":"Chay-intr","sequence":"first","affiliation":[{"name":"School of Engineering, Tokyo Institute of Technology"}]},{"given":"Hidetaka","family":"Kamigaito","sequence":"additional","affiliation":[{"name":"Division of Information Science, Nara Institute of Science and Technology"}]},{"given":"Kotaro","family":"Funakoshi","sequence":"additional","affiliation":[{"name":"Institute of Innovative Research, Tokyo Institute of Technology"}]},{"given":"Manabu","family":"Okumura","sequence":"additional","affiliation":[{"name":"Institute of Innovative Research, Tokyo Institute of Technology"}]}],"member":"3685","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"Aho, A. V. and Corasick, M. J. (1975). \u201cEfficient String Matching: An Aid to Bibliographic Search.\u201d <i>Communication of the ACM<\/i>, 18 (6), pp. 333\u2013340.","DOI":"10.1145\/360825.360855"},{"key":"2","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2015). \u201cNeural Machine Translation by Jointly Learning to Align and Translate.\u201d In Bengio, Y. and LeCun, Y. (Eds.), <i>3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings<\/i>."},{"key":"3","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., and Mikolov, T. (2017). \u201cEnriching Word Vectors with Subword Information.\u201d <i>Transactions of the Association for Computational Linguistics<\/i>, 5, pp. 135\u2013146.","DOI":"10.1162\/tacl_a_00051"},{"key":"4","doi-asserted-by":"crossref","unstructured":"Breiman, L. (1994). \u201cBagging Predictors.\u201d <i>Machine Learning<\/i>, 24 (2), pp. 114\u2013133.","DOI":"10.1007\/BF00058655"},{"key":"5","unstructured":"Chay-intr, T., Kamigaito, H., and Okumura, M. (2021). \u201cCharacter-based Thai Word Segmentation with Multiple Attentions.\u201d In <i>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)<\/i>, pp. 264\u2013273, Held Online. INCOMA Ltd."},{"key":"6","doi-asserted-by":"crossref","unstructured":"Chen, X., Shi, Z., Qiu, X., and Huang, X. (2017). \u201cAdversarial Multi-Criteria Learning for Chinese Word Segmentation.\u201d In <i>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 1193\u20131203, Vancouver, Canada. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P17-1110"},{"key":"7","unstructured":"Chormai, P., Prasertsom, P., and T. Rutherford, A. (2019). \u201cAttaCut: A Fast and Accurate Neural Thai Word Segmenter.\u201d https:\/\/arxiv.org\/abs\/1911.07056."},{"key":"8","unstructured":"Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., and Kuksa, P. (2011). \u201cNatural Language Processing (almost) from Scratch.\u201d <i>Journal of Machine Learning Research<\/i>, 12, pp. 2493\u20132537."},{"key":"9","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). \u201cBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.\u201d In <i>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)<\/i>, pp. 4171\u20134186, Minneapolis, Minnesota. Association for Computational Linguistics."},{"key":"10","doi-asserted-by":"crossref","unstructured":"Dyer, C., Muresan, S., and Resnik, P. (2008). \u201cGeneralizing Word Lattice Translation.\u201d In <i>Proceedings of ACL-08: HLT<\/i>, pp. 1012\u20131020, Columbus, Ohio. Association for Computational Linguistics.","DOI":"10.21236\/ADA482158"},{"key":"11","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017). \u201cModel-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.\u201d https:\/\/arxiv.org\/abs\/1703.03400."},{"key":"12","doi-asserted-by":"crossref","unstructured":"Gers, F., Schmidhuber, J., and Cummins, F. (2000). \u201cLearning to Forget: Continual Prediction with LSTM.\u201d <i>Neural Computation<\/i>, 12 (10), pp. 2451\u20132471.","DOI":"10.1162\/089976600300015015"},{"key":"13","doi-asserted-by":"crossref","unstructured":"Gui, T., Zou, Y., Zhang, Q., Peng, M., Fu, J., Wei, Z., and Huang, X. (2019). \u201cA Lexicon-Based Graph Neural Network for Chinese NER.\u201d In <i>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)<\/i>, pp. 1040\u20131050, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1096"},{"key":"14","unstructured":"He, H., Wu, L., Yan, H., Gao, Z., Feng, Y., and Townsend, G. (2017). \u201cEffective Neural Solution for Multi-Criteria Word Segmentation.\u201d https:\/\/arxiv.org\/abs\/1712.02856."},{"key":"15","doi-asserted-by":"crossref","unstructured":"Higashiyama, S., Utiyama, M., Sumita, E., Ideuchi, M., Oida, Y., Sakamoto, Y., and Okada, I. (2019). \u201cIncorporating Word Attention into Character-Based Word Segmentation.\u201d In <i>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)<\/i>, pp. 2699\u20132709, Minneapolis, Minnesota. Association for Computational Linguistics.","DOI":"10.18653\/v1\/N19-1276"},{"key":"16","doi-asserted-by":"crossref","unstructured":"Hochreiter, S. and Schmidhuber, J. (1997). \u201cLong Short-Term Memory.\u201d <i>Neural Computation<\/i>, 9 (8), pp. 1735\u20131780.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"17","doi-asserted-by":"crossref","unstructured":"Huang, K., Huang, D., Liu, Z., and Mo, F. (2020). \u201cA Joint Multiple Criteria Model in Transfer Learning for Cross-domain Chinese Word Segmentation.\u201d In <i>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)<\/i>, pp. 3873\u20133882, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-main.318"},{"key":"18","doi-asserted-by":"crossref","unstructured":"Huang, K., Yu, H., Liu, J., Liu, W., Cao, J., and Huang, D. (2021). \u201cLexicon-Based Graph Convolutional Network for Chinese Word Segmentation.\u201d In <i>Findings of the Association for Computational Linguistics: EMNLP 2021<\/i>, pp. 2908\u20132917, Punta Cana, Dominican Republic. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.findings-emnlp.248"},{"key":"19","doi-asserted-by":"crossref","unstructured":"Huang, W., Cheng, X., Chen, K., Wang, T., and Chu, W. (2020). \u201cTowards Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning.\u201d In <i>Proceedings of the 28th International Conference on Computational Linguistics<\/i>, pp. 2062\u20132072, Barcelona, Spain (Online). International Committee on Computational Linguistics.","DOI":"10.18653\/v1\/2020.coling-main.186"},{"key":"20","unstructured":"Huang, Z., Xu, W., and Yu, K. (2015). \u201cBidirectional LSTM-CRF Models for Sequence Tagging.\u201d."},{"key":"21","doi-asserted-by":"crossref","unstructured":"Ke, Z., Shi, L., Sun, S., Meng, E., Wang, B., and Qiu, X. (2021). \u201cPre-training with Meta Learning for Chinese Word Segmentation.\u201d In <i>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 5514\u20135523, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.naacl-main.436"},{"key":"22","unstructured":"Kipf, T. N. and Welling, M. (2016). \u201cSemi-Supervised Classification with Graph Convolutional Networks.\u201d https:\/\/arxiv.org\/abs\/1609.02907."},{"key":"23","unstructured":"Kitagawa, Y. and Komachi, M. (2018). \u201cLong Short-Term Memory for Japanese Word Segmentation.\u201d In <i>Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation<\/i>, Hong Kong. Association for Computational Linguistics."},{"key":"24","unstructured":"Kittinaradorn, R., Achakulvisut, T., Chaovavanich, K., Srithaworn, K., Chormai, P., Kaewkasi, C., Ruangrong, T., and Oparad, K. (2019). \u201cDeepCut: A Thai word tokenization library using Deep Neural Network.\u201d https:\/\/github.com\/rkcosmos\/deepcut."},{"key":"25","unstructured":"Lafferty, J., Mccallum, A., and Pereira, F. (2001). \u201cConditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data.\u201d In <i>Proceedings of the 18th International Conference on Machine Learning<\/i>, pp. 282\u2013289."},{"key":"26","doi-asserted-by":"crossref","unstructured":"Lai, Y., Liu, Y., Feng, Y., Huang, S., and Zhao, D. (2021). \u201cLattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models.\u201d In <i>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 1716\u20131731, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.naacl-main.137"},{"key":"27","doi-asserted-by":"crossref","unstructured":"Lapjaturapit, T., Viriyayudhakom, K., and Theeramunkong, T. (2018). \u201cMulti-Candidate Word Segmentation using Bi-directional LSTM Neural Networks.\u201d In <i>Proceedings of 2018 International Conference on Embedded Systems and Intelligent Technology and International Conference on Information and Communication Technology for Embedded Systems<\/i>, pp. 30\u201335.","DOI":"10.1109\/ICESIT-ICICTES.2018.8442053"},{"key":"28","doi-asserted-by":"crossref","unstructured":"Li, X., Yan, H., Qiu, X., and Huang, X. (2020). \u201cFLAT: Chinese NER Using Flat-Lattice Transformer.\u201d In <i>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 6836\u20136842, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.611"},{"key":"29","doi-asserted-by":"crossref","unstructured":"Li, X., Meng, Y., Sun, X., Han, Q., Yuan, A., and Li, J. (2019). \u201cIs Word Segmentation Necessary for Deep Learning of Chinese Representations?\u201d In <i>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 3242\u20133252, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1314"},{"key":"30","doi-asserted-by":"crossref","unstructured":"Limkonchotiwat, P., Phatthiyaphaibun, W., Sarwar, R., Chuangsuwanich, E., and Nutanong, S. (2021). \u201cHandling Cross- and Out-of-Domain Samples in Thai Word Segmentation.\u201d In <i>Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021<\/i>, pp. 1003\u20131016, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.findings-acl.86"},{"key":"31","unstructured":"Loshchilov, I. and Hutter, F. (2017). \u201cDecoupled Weight Decay Regularization.\u201d https:\/\/arxiv.org\/abs\/1711.05101."},{"key":"32","doi-asserted-by":"crossref","unstructured":"Maimaiti, M., Liu, Y., Zheng, Y., Chen, G., Huang, K., Zhang, J., Luan, H., and Sun, M. (2021). \u201cSegment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision.\u201d In <i>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 2068\u20132077, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.emnlp-main.158"},{"key":"33","unstructured":"Neubig, G., Nakata, Y., and Mori, S. (2011). \u201cPointwise Prediction for Robust, Adaptable Japanese Morphological Analysis.\u201d In <i>Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 529\u2013533, Portland, Oregon, USA. Association for Computational Linguistics."},{"key":"34","unstructured":"Qian, X. and Liu, Y. (2012). \u201cJoint Chinese Word Segmentation, POS Tagging and Parsing.\u201d In <i>Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning<\/i>, pp. 501\u2013511, Jeju Island, Korea. Association for Computational Linguistics."},{"key":"35","doi-asserted-by":"crossref","unstructured":"Qiu, X., Pei, H., Yan, H., and Huang, X. (2020). \u201cA Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder.\u201d In <i>Findings of the Association for Computational Linguistics: EMNLP 2020<\/i>, pp. 2887\u20132897, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.findings-emnlp.260"},{"key":"36","unstructured":"Seeha, S., Bilan, I., Mamani Sanchez, L., Huber, J., Matuschek, M., and Sch\u00fctze, H. (2020). \u201cThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation.\u201d In <i>Proceedings of the 12th Language Resources and Evaluation Conference<\/i>, pp. 6947\u20136957, Marseille, France. European Language Resources Association."},{"key":"37","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., and Birch, A. (2016). \u201cNeural Machine Translation of Rare Words with Subword Units.\u201d In <i>Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 1715\u20131725, Berlin, Germany. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P16-1162"},{"key":"38","unstructured":"Shen, Y., Tan, S., Sordoni, A., and Courville, A. (2018). \u201cOrdered Neurons: Integrating Tree Structures into Recurrent Neural Networks.\u201d https:\/\/arxiv.org\/abs\/1810.09536."},{"key":"39","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Ruslan, S. (2014). \u201cDropout: A Simple Way to Prevent Neural Networks from Overfitting.\u201d <i>Journal of Machine Learning Research<\/i>, 15, pp. 1929\u20131958."},{"key":"40","unstructured":"Sun, W. (2010). \u201cWord-based and Character-based Word Segmentation Models: Comparison and Combination.\u201d In <i>Coling 2010: Posters<\/i>, pp. 1211\u20131219, Beijing, China. Coling 2010 Organizing Committee."},{"key":"41","unstructured":"Tang, X., Wang, J., and Su, Q. (2022). \u201cChinese Word Segmentation with Heterogeneous Graph Neural Network.\u201d https:\/\/arxiv.org\/abs\/2201.08975."},{"key":"42","doi-asserted-by":"crossref","unstructured":"Tian, Y., Song, Y., Ao, X., Xia, F., Quan, X., Zhang, T., and Wang, Y. (2020a). \u201cJoint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge.\u201d In <i>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 8286\u20138296, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.735"},{"key":"43","doi-asserted-by":"crossref","unstructured":"Tian, Y., Song, Y., Xia, F., Zhang, T., and Wang, Y. (2020b). \u201cImproving Chinese Word Segmentation with Wordhood Memory Networks.\u201d In <i>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 8274\u20138285, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.734"},{"key":"44","unstructured":"Treeratpituk, P. (2017). \u201cThai Word-Segmentation with LSTM in Tensorflow.\u201d https:\/\/github.com\/pucktada\/cutkum."},{"key":"45","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). \u201cAttention Is All You Need.\u201d https:\/\/arxiv.org\/abs\/1706.03762."},{"key":"46","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (2017). \u201cGraph Attention Networks.\u201d https:\/\/arxiv.org\/abs\/1710.10903."},{"key":"47","doi-asserted-by":"crossref","unstructured":"Wang, X., Ji, H., Shi, C., Wang, B., Cui, P., Yu, P., and Ye, Y. (2019). \u201cHeterogeneous Graph Attention Network.\u201d.","DOI":"10.1145\/3308558.3313562"},{"key":"48","unstructured":"Yang, H. (2019). \u201cBERT Meets Chinese Word Segmentation.\u201d https:\/\/arxiv.org\/abs\/1909.09292."},{"key":"49","unstructured":"Yang, J., Zhang, Y., and Liang, S. (2019). \u201cSubword Encoding in Lattice LSTM for Chinese Word Segmentation.\u201d In <i>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)<\/i>, pp. 2720\u20132725, Minneapolis, Minnesota. Association for Computational Linguistics."},{"key":"50","unstructured":"Yao, L., Mao, C., and Luo, Y. (2018). \u201cGraph Convolutional Networks for Text Classification.\u201d https:\/\/arxiv.org\/abs\/1809.05679."},{"key":"51","doi-asserted-by":"crossref","unstructured":"Zhang, Y. and Yang, J. (2018). \u201cChinese NER Using Lattice LSTM.\u201d In <i>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 1554\u20131564, Melbourne, Australia. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P18-1144"}],"container-title":["Journal of Natural Language Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/30\/2\/30_456\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T04:28:14Z","timestamp":1686976094000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/30\/2\/30_456\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.5715\/jnlp.30.456","relation":{},"ISSN":["1340-7619","2185-8314"],"issn-type":[{"value":"1340-7619","type":"print"},{"value":"2185-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}