{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:49:17Z","timestamp":1776887357745,"version":"3.51.2"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2020AAA0106501"],"award-info":[{"award-number":["2020AAA0106501"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61976072 and 61772153"],"award-info":[{"award-number":["61976072 and 61772153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2022,5,31]]},"abstract":"<jats:p>Spoken language is fundamentally different from the written language in that it contains frequent disfluencies or parts of an utterance that are corrected by the speaker. Disfluency detection (removing these disfluencies) is desirable to clean the input for use in downstream NLP tasks. Most existing approaches to disfluency detection heavily rely on human-annotated data, which is scarce and expensive to obtain in practice. To tackle the training data bottleneck, in this work, we investigate methods for combining self-supervised learning and active learning for disfluency detection. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled data and propose two self-supervised pre-training tasks: (i) a tagging task to detect the added noisy words and (ii) sentence classification to distinguish original sentences from grammatically incorrect sentences. We then combine these two tasks to jointly pre-train a neural network. The pre-trained neural network is then fine-tuned using human-annotated disfluency detection training data. The self-supervised learning method can capture task-special knowledge for disfluency detection and achieve better performance when fine-tuning on a small annotated dataset compared to other supervised methods. However, limited in that the pseudo training data are generated based on simple heuristics and cannot fully cover all the disfluency patterns, there is still a performance gap compared to the supervised models trained on the full training dataset. We further explore how to bridge the performance gap by integrating active learning during the fine-tuning process. Active learning strives to reduce annotation costs by choosing the most critical examples to label and can address the weakness of self-supervised learning with a small annotated dataset. We show that by combining self-supervised learning with active learning, our model is able to match state-of-the-art performance with just about 10% of the original training data on both the commonly used English Switchboard test set and a set of in-house annotated Chinese data.<\/jats:p>","DOI":"10.1145\/3487290","type":"journal-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T14:36:25Z","timestamp":1639406185000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Combining Self-supervised Learning and Active Learning for Disfluency Detection"],"prefix":"10.1145","volume":"21","author":[{"given":"Shaolei","family":"Wang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, HeiLongJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, HeiLongJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanxiang","family":"Che","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, HeiLongJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sendong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, HeiLongJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, HeiLongJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,12,13]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.13"},{"key":"e_1_3_2_3_2","first-page":"4230","article-title":"Noisy BiLSTM-based models for disfluency detection","author":"Bach Nguyen","year":"2019","unstructured":"Nguyen Bach and Fei Huang. 2019. Noisy BiLSTM-based models for disfluency detection. In Proceedings of the INTERSPEECH Conference (INTERSPEECH\u201919). 4230\u20134234.","journal-title":"Proceedings of the INTERSPEECH Conference (INTERSPEECH\u201919)"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944966"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2026"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.3115\/1073336.1073352"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1082"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/1619410.1619452"},{"key":"e_1_3_2_9_2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL\u201919).","journal-title":"Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL\u201919)"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016351"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.638"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1029"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/1620853.1620885"},{"key":"e_1_3_2_16_2","article-title":"Discriminative active learning","author":"Gissin Daniel","year":"2019","unstructured":"Daniel Gissin and Shai Shalev-Shwartz. 2019. Discriminative active learning. arXiv:1907.06347. Retrieved from https:\/\/arxiv.org\/abs\/1907.06347.","journal-title":"arXiv:1907.06347"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/1895550.1895693"},{"key":"e_1_3_2_18_2","article-title":"Bridging nonlinearities and stochastic regularizers with gaussian error linear units","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Bridging nonlinearities and stochastic regularizers with gaussian error linear units. arXiv:1606.08415. Retrieved from https:\/\/arxiv.org\/abs\/1606.08415.","journal-title":"arXiv:1606.08415"},{"key":"e_1_3_2_19_2","article-title":"Joint incremental disfluency detection and dependency parsing","volume":"2","author":"Honnibal Matthew","year":"2014","unstructured":"Matthew Honnibal and Mark Johnson. 2014. Joint incremental disfluency detection and dependency parsing. Trans. Assoc. Comput. Linguist. 2 (2014).","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-264"},{"key":"e_1_3_2_21_2","first-page":"4610","volume-title":"Proceedings of the Empirical Methods in Natural Language Processing (EMNLP\u201918)","author":"Lou Paria Jamshid","year":"2018","unstructured":"Paria Jamshid Lou, Peter Anderson, and Mark Johnson. 2018. Disfluency detection using auto-correlational neural networks. In Proceedings of the Empirical Methods in Natural Language Processing (EMNLP\u201918). 4610\u20134619."},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Paria Jamshid Lou Yufei Wang and Mark Johnson. 2019. Neural constituency parsing of speech transcripts. In Proceedings of the 2019 Conference of the North American Volume 1. 2756\u20132765.","DOI":"10.18653\/v1\/N19-1282"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218960"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/188490.188495"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-1033"},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Ting Liu Yiming Cui Qingyu Yin Weinan Zhang Shijin Wang and Guoping Hu. 2016. Generating and exploiting large-scale pseudo training data for zero pronoun resolution. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) . 102\u2013111.","DOI":"10.18653\/v1\/P17-1010"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Paria Jamshid Lou and Mark Johnson. 2017. Disfluency detection using a noisy channel model and a deep neural language model. In Proceedings of ACL (Volume 2: Short Papers) . 547\u2013553.","DOI":"10.18653\/v1\/P17-2087"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Paria Jamshid Lou and Mark Johnson. 2020. Improving disfluency detection by self-training a self-attentive model In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics . 3754\u20133763.","DOI":"10.18653\/v1\/2020.acl-main.346"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of Conference of the European Chapter of the Association for Computational Linguistics (EACL\u201917)","author":"Alonso H\u00e9ctor Mart\u00ednez","year":"2017","unstructured":"H\u00e9ctor Mart\u00ednez Alonso and Barbara Plank. 2017. When is multitask learning effective? Semantic sequence prediction under varying data conditions. In Proceedings of Conference of the European Chapter of the Association for Computational Linguistics (EACL\u201917)."},{"key":"e_1_3_2_30_2","volume-title":"Dysfluency Annotation Stylebook for the Switchboard Corpus","author":"Meteer Marie W.","year":"1995","unstructured":"Marie W. Meteer, Ann A. Taylor, Robert MacIntyre, and Rukmini Iyer. 1995. Dysfluency Annotation Stylebook for the Switchboard Corpus. University of Pennsylvania."},{"key":"e_1_3_2_31_2","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. Computer Science ."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999959"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-604"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1186"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-1015"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1417"},{"key":"e_1_3_2_38_2","first-page":"820","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL\u201913)","author":"Qian Xian","year":"2013","unstructured":"Xian Qian and Yang Liu. 2013. Disfluency detection using multi-step stacked learning. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL\u201913). 820\u2013825."},{"key":"e_1_3_2_39_2","volume-title":"Improving Language Understanding with Unsupervised Learning","author":"Radford Alec","year":"2018","unstructured":"Alec Radford, Karthik Narasimhan, Time Salimans, and Ilya Sutskever. 2018. Improving Language Understanding with Unsupervised Learning. Technical Report. OpenAI."},{"key":"e_1_3_2_40_2","first-page":"124","volume-title":"Proceedings of the Empirical Methods in Natural Language Processing (EMNLP\u201913)","author":"Rasooli Mohammad Sadegh","year":"2013","unstructured":"Mohammad Sadegh Rasooli and Joel R. Tetreault. 2013. Joint parsing and disfluency detection in linear time. In Proceedings of the Empirical Methods in Natural Language Processing (EMNLP\u201913). 124\u2013129."},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Dongyu Ru Yating Luo Lin Qiu Hao Zhou Lei Li Weinan Zhang and Yong Yu. 2020. Active sentence learning by adversarial uncertainty sampling in discrete space. In Findings of the Association for Computational Linguistics: EMNLP 2020 . 4908\u20134917.","DOI":"10.18653\/v1\/2020.findings-emnlp.441"},{"key":"e_1_3_2_42_2","unstructured":"Ozan Sener and Silvio Savarese. 2017. Active learning for convolutional neural networks: A core-set approach. In International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=H1aIuk-RW."},{"key":"e_1_3_2_43_2","volume-title":"Active Learning Literature Survey","author":"Settles Burr","year":"2009","unstructured":"Burr Settles. 2009. Active Learning Literature Survey. Technical Report. University of Wisconsin\u2014Madison Department of Computer Sciences."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2630"},{"key":"e_1_3_2_45_2","volume-title":"Preliminaries to a Theory of Speech Disfluencies","author":"Shriberg Elizabeth Ellen","year":"1994","unstructured":"Elizabeth Ellen Shriberg. 1994. Preliminaries to a Theory of Speech Disfluencies. Ph.D. Dissertation. Citeseer."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1318"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023119"},{"key":"e_1_3_2_48_2","unstructured":"Zhaopeng Tu Zhengdong Lu Yang Liu Xiaohua Liu and Hang Li. 2016. Modeling coverage for neural machine translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_50_2","volume-title":"Proceedings of the International Conference on Computational Linguistics (COLING\u201918)","author":"Wang Feng","year":"2018","unstructured":"Feng Wang, Wei Chen, Zhen Yang, Qianqian Dong, Shuang Xu, and Bo Xu. 2018. Semi-supervised disfluency detection. In Proceedings of the International Conference on Computational Linguistics (COLING\u201918)."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6456"},{"key":"e_1_3_2_52_2","volume-title":"Proceedings of the International Conference on Computational Linguistics (COLING\u201916)","author":"Wang Shaolei","year":"2016","unstructured":"Shaolei Wang, Wanxiang Che, and Ting Liu. 2016. A neural attention model for disfluency detection. In Proceedings of the International Conference on Computational Linguistics (COLING\u201916)."},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1296"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1048"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1109"},{"key":"e_1_3_2_57_2","article-title":"Robust cross-domain disfluency detection with pattern match networks","author":"Zayats Vicky","year":"2018","unstructured":"Vicky Zayats and Mari Ostendorf. 2018. Robust cross-domain disfluency detection with pattern match networks. arXiv:1811.07236. Retrieved from https:\/\/arxiv.org\/abs\/1811.07236.","journal-title":"arXiv:1811.07236"},{"key":"e_1_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Vicky Zayats and Mari Ostendorf. 2019. Giving attention to the unexpected: Using prosody innovations in disfluency detection. In Proceedings of the 2019 Conference of the North American . Minneapolis Minnesota 86\u201395.","DOI":"10.18653\/v1\/N19-1008"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-603"},{"key":"e_1_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Vicky Zayats Mari Ostendorf and Hannaneh Hajishirzi. 2016. Disfluency detection using a bidirectional LSTM. In INTERSPEECH .","DOI":"10.21437\/Interspeech.2016-1247"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298060"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.162"},{"key":"e_1_3_2_63_2","first-page":"1371","volume-title":"Proceedings of the International Conference on Computational Linguistics (COLING\u201910)","author":"Zwarts Simon","year":"2010","unstructured":"Simon Zwarts, Mark Johnson, and Robert Dale. 2010. Detecting speech repairs incrementally using a noisy channel approach. In Proceedings of the International Conference on Computational Linguistics (COLING\u201910). 1371\u20131378."}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487290","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3487290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:48Z","timestamp":1750191528000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3487290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5,31]]}},"alternative-id":["10.1145\/3487290"],"URL":"https:\/\/doi.org\/10.1145\/3487290","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,13]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}