{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:33:34Z","timestamp":1763202814284,"version":"build-2065373602"},"reference-count":56,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"],"award-info":[{"award-number":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Plan","award":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"],"award-info":[{"award-number":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"]}]},{"name":"Guangdong Province Key Research and Development Plan","award":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"],"award-info":[{"award-number":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"]}]},{"name":"Major Key Project of PCL","award":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"],"award-info":[{"award-number":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"]}]},{"name":"Joint Research Fund of Guangzhou and University","award":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"],"award-info":[{"award-number":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"]}]},{"name":"Guangdong Higher Education Innovation Group","award":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"],"award-info":[{"award-number":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"]}]},{"name":"Guangdong Province Universities and Colleges Pearl River Scholar Funded Scheme","award":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"],"award-info":[{"award-number":["62272114","2018YFB1800702","2021YFB2012402","2019B010136003","PCL2022A03","PCL2021A02","PCL2021A09","202201020380","2020KCXTD007","2019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Implicit discourse relation recognition (IDRR) has long been considered a challenging problem in shallow discourse parsing. The absence of connectives makes such relations implicit and requires much more effort to understand the semantics of the text. Thus, it is important to preserve the semantic completeness before any attempt to predict the discourse relation. However, word level embedding, widely used in existing works, may lead to a loss of semantics by splitting some phrases that should be treated as complete semantic units. In this article, we proposed three methods to segment a sentence into complete semantic units: a corpus-based method to serve as the baseline, a constituent parsing tree-based method, and a dependency parsing tree-based method to provide a more flexible and automatic way to divide the sentence. The segmented sentence will then be embedded at the level of semantic units so the embeddings could be fed into the IDRR networks and play the same role as word embeddings. We implemented our methods into one of the recent IDRR models to compare the performance with the original version using word level embeddings. Results show that proper embedding level better conserves the semantic information in the sentence and helps to enhance the performance of IDRR models.<\/jats:p>","DOI":"10.3390\/e25091294","type":"journal-article","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T10:14:11Z","timestamp":1693822451000},"page":"1294","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Conserving Semantic Unit Information and Simplifying Syntactic Constituents to Improve Implicit Discourse Relation Recognition"],"prefix":"10.3390","volume":"25","author":[{"given":"Zhongyang","family":"Fang","sequence":"first","affiliation":[{"name":"The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Yue","family":"Cong","sequence":"additional","affiliation":[{"name":"The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Yuhan","family":"Chai","sequence":"additional","affiliation":[{"name":"The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Chengliang","family":"Gao","sequence":"additional","affiliation":[{"name":"The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Ximing","family":"Chen","sequence":"additional","affiliation":[{"name":"The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China"}]},{"given":"Jing","family":"Qiu","sequence":"additional","affiliation":[{"name":"The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,4]]},"reference":[{"key":"ref_1","first-page":"7","article-title":"Survey of Implicit Discourse Relation Recognition Based on Deep Learning","volume":"47","author":"Hu","year":"2020","journal-title":"Comput. Sci."},{"key":"ref_2","first-page":"281","article-title":"A systematic study of neural discourse models for implicit discourse relation","volume":"Volume 1","author":"Rutherford","year":"2017","journal-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics"},{"doi-asserted-by":"crossref","unstructured":"Xue, N., Ng, H.T., Pradhan, S., Prasad, R., Bryant, C., and Rutherford, A. (2015, January 30\u201331). The conll-2015 shared task on shallow discourse parsing. Proceedings of the Nineteenth Conference on Computational Natural Language Learning-Shared Task (CoNLL \u201915), Beijing, China.","key":"ref_3","DOI":"10.18653\/v1\/K15-2001"},{"doi-asserted-by":"crossref","unstructured":"Xue, N., Ng, H.T., Pradhan, S., Rutherford, A., Webber, B., Wang, C., and Wang, H. (2016, January 7\u201312). Conll 2016 shared task on multilingual shallow discourse parsing. Proceedings of the Twentieth Conference on Computational Natural Language Learning-Shared Task (CoNLL \u201916), Berlin, Germany.","key":"ref_4","DOI":"10.18653\/v1\/K16-2001"},{"doi-asserted-by":"crossref","unstructured":"Gerani, S., Mehdad, Y., Carenini, G., Ng, R., and Nejat, B. (2014, January 25\u201329). Abstractive summarization of product reviews using discourse structure. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP \u201914), Doha, Qatar.","key":"ref_5","DOI":"10.3115\/v1\/D14-1168"},{"unstructured":"Louis, A., Joshi, A.K., and Nenkova, A. (2010, January 24\u201325). Discourse indicators for content selection in Summarization. Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL \u201910), Tokyo, Japan.","key":"ref_6"},{"doi-asserted-by":"crossref","unstructured":"Yoshida, Y., Suzuki, J., Hirao, T., and Nagata, M. (2014, January 25\u201329). Dependency-based discourse parser for single-document summarization. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP \u201914), Doha, Qatar.","key":"ref_7","DOI":"10.3115\/v1\/D14-1196"},{"key":"ref_8","first-page":"977","article-title":"Discourse complements lexical semantics for non-factoid answer reranking","volume":"Volume 1","author":"Jansen","year":"2014","journal-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL \u201914)"},{"unstructured":"Liakata, M., Dobnik, S., Saha, S., Batchelor, C., and Schuhmann, D.R. (2013, January 18\u201321). A discourse-driven content model for summarising scientific articles evaluated in a complex question answering task. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP \u201913), Seattle, WA, USA.","key":"ref_9"},{"unstructured":"Verberne, S., Boves, L., Oostdijk, N., and Coppen, P.-A. (2007, January 23\u201327). Evaluating discourse-based answer extraction for why-question answering. Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201907), Amsterdam, The Netherlands.","key":"ref_10"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.1109\/JIOT.2020.3002255","article-title":"CorrAUC: A malicious bot-iot traffic detection method in iot network using machine-learning techniques","volume":"8","author":"Shafiq","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_12","first-page":"4754","article-title":"Dynamic Prototype Network based on Sample Adaptation for Few-Shot Malware Detection","volume":"35","author":"Chai","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_13","first-page":"69","article-title":"Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation","volume":"Volume 2","author":"McKeown","year":"2013","journal-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL\u201913)"},{"unstructured":"Blair-Goldensohn, S., McKeown, K., and Rambow, O. (2007). Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference (NAACL \u201907), Rochester, NY, USA, 22\u201327 April 2007, The Association for Computational Linguistics.","key":"ref_14"},{"doi-asserted-by":"crossref","unstructured":"Pitler, E., Louis, A., and Nenkova, A. (2009, January 2\u20137). Automatic sense prediction for implicit discourse relations in text. Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL \u201909), Singapore.","key":"ref_15","DOI":"10.3115\/1690219.1690241"},{"unstructured":"Pitler, E., Raghupathy, M., Mehta, H., Nenkova, A., Lee, A., and Joshi, A.K. (2008, January 18\u201322). Easily Identifiable Discourse Relations. Proceedings of the 22nd International Conference on Computational Linguistics, Posters Proceedings (COLING \u201908), Manchester, UK.","key":"ref_16"},{"doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, J., and Zong, C. (2015, January 13\u201314). Predicting Implicit Discourse Relations with Purely Distributed Representations. Proceedings of the Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, Guangzhou, China. Lecture Notes in Computer Science.","key":"ref_17","DOI":"10.1007\/978-3-319-25816-4_24"},{"doi-asserted-by":"crossref","unstructured":"Li, J.J., and Nenkova, A. (2014, January 18\u201320). Reducing sparsity improves the recognition of implicit discourse relations. Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL\u201914), Philadelphia, PA, USA.","key":"ref_18","DOI":"10.3115\/v1\/W14-4327"},{"unstructured":"Zhou, Z.M., Lan, M., Niu, Z.-Y., Xu, Y., and Su, J. (2010, January 24\u201325). The effects of discourse connectives prediction on implicit discourse relation recognition. Proceedings of the SIGDIAL 2010 Conference (SIGDIAL \u201910), Tokyo, Japan.","key":"ref_19"},{"unstructured":"Zhou, Z.-M., Xu, Y., Niu, Z.-Y., Lan, M., Su, J., and Tan, C.L. (2010, January 23\u201327). Predicting discourse connectives for implicit discourse relation recognition. Proceedings of the 23rd International Conference on Computational Linguistics: Posters (COLING \u201910), Beijing, China.","key":"ref_20"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"101863","DOI":"10.1016\/j.cose.2020.101863","article-title":"IoT malicious traffic identification using wrapper-based feature selection mechanisms","volume":"94","author":"Shafiq","year":"2020","journal-title":"Comput. Secur."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"4248","DOI":"10.1109\/TNSM.2022.3200866","article-title":"From Data and Model Levels: Improve the Performance of Few-Shot Malware Classification","volume":"19","author":"Chai","year":"2022","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"doi-asserted-by":"crossref","unstructured":"Liu, X., Ou, J., Song, Y., and Jiang, X. (2020, January 11\u201317). On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI\u201920), Yokohama, Japan.","key":"ref_23","DOI":"10.24963\/ijcai.2020\/530"},{"doi-asserted-by":"crossref","unstructured":"Wang, S., Thompson, L., and Iyyer, M. (2021, January 7\u201311). Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online.","key":"ref_24","DOI":"10.18653\/v1\/2021.emnlp-main.846"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.ins.2019.12.031","article-title":"Phrase2Vec: Phrase embedding based on parsing","volume":"517","author":"Wu","year":"2019","journal-title":"Inf. Sci."},{"unstructured":"Prasad, R., Dinesh, N., Lee, A., Miltsakaki, E., Robaldo, L., Joshi, A.K., and Webber, B.L. (June, January 26). The Penn Discourse TreeBank 2.0. Proceedings of the International Conference on Language Resources and Evaluation (LREC \u201908), Marrakech, Morocco.","key":"ref_26"},{"doi-asserted-by":"crossref","unstructured":"Bosselut, A., Celikyilmaz, A., He, X., Gao, J., Huang, P.S., and Choi, Y. (2018, January 1\u20136). Discourse-aware neural rewards for coherent text generation. Proceedings of the NAACL-HLT, New Orleans, LA, USA.","key":"ref_27","DOI":"10.18653\/v1\/N18-1016"},{"doi-asserted-by":"crossref","unstructured":"Cohan, A., Dernoncourt, F., Kim, D.S., Bui, T., Kim, S., Chang, W., and Goharian, N. (2018, January 1\u20136). A discourse-aware attention model for abstractive summarization of long documents. Proceedings of the NAACL-HLT, New Orleans, LA, USA.","key":"ref_28","DOI":"10.18653\/v1\/N18-2097"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1162\/COLI_a_00291","article-title":"Hybrid Grammars for Parsing of Discontinuous Phrase Structures and Non-Projective Dependency Structures","volume":"43","author":"Gebhardt","year":"2017","journal-title":"Comput. Linguist."},{"doi-asserted-by":"crossref","unstructured":"Jie, Z., Muis, A., and Lu, W. (2017, January 4\u20139). Efficient dependency-guided named entity recognition. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","key":"ref_30","DOI":"10.1609\/aaai.v31i1.11009"},{"doi-asserted-by":"crossref","unstructured":"Liu, J., Shang, J., Wang, C., Ren, X., and Han, J. (June, January 31). Mining quality phrases from massive text corpora. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, ACM, Melbourne, VIC, Australia.","key":"ref_31","DOI":"10.1145\/2723372.2751523"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1613\/jair.4761","article-title":"Integrating rules and dictionaries from shallow-transfer machine translation into phrase-based statistical machine translation","volume":"55","year":"2016","journal-title":"J. Artif. Intell. Res."},{"key":"ref_33","first-page":"2063","article-title":"Pattern for python","volume":"13","author":"Daelemans","year":"2012","journal-title":"J. Mach. Learn. Res."},{"unstructured":"Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv.","key":"ref_34"},{"unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., and Dean, J. (2013). Advances in Neural Information Processing Systems, MIT Press.","key":"ref_35"},{"doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., and Manning, C.D. (2014, January 25\u201329). Glove: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP \u201914), Doha, Qatar.","key":"ref_36","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1162\/tacl_a_00135","article-title":"Learning composition models for phrase embeddings","volume":"3","author":"Yu","year":"2015","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"102422","DOI":"10.1016\/j.ipm.2020.102422","article-title":"Phrase embedding learning from internal and external information based on autoencoder","volume":"58","author":"Li","year":"2020","journal-title":"Inf. Process. Manag."},{"doi-asserted-by":"crossref","unstructured":"Lei, W., Xiang, Y., Wang, Y., Zhong, Q., Liu, M., and Kan, M.Y. (2018, January 2\u20137). Linguistic properties matter for implicit discourse relation recognition: Combining semantic interaction, topic continuity and attribution. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","key":"ref_39","DOI":"10.1609\/aaai.v32i1.11933"},{"doi-asserted-by":"crossref","unstructured":"Zhang, N., Deng, S., Sun, Z., Wang, G., Chen, X., Zhang, W., and Chen, H. (2019). Long-tail relation extraction via knowledge graph embeddings and graph convolution networks. arXiv.","key":"ref_40","DOI":"10.18653\/v1\/N19-1306"},{"unstructured":"Gao, T., Han, X., Liu, Z., and Sun, M. (February, January 27). Hybrid attention-based prototypical networks for noisy few-shot relation classification. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.","key":"ref_41"},{"doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, N., Xie, X., Deng, S., Yao, Y., Tan, C., Huang, F., Si, L., and Chen, H. (2022, January 25\u201329). Knowprompt: Knowledge-aware prompt-tuning with synergistic optimization for relation extraction. Proceedings of the ACM Web Conference, Virtual.","key":"ref_42","DOI":"10.1145\/3485447.3511998"},{"unstructured":"Wei, S., and Demberg, V. (2019, January 3\u20137). Next sentence prediction helps implicit discourse relation classification within and across domains. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","key":"ref_43"},{"unstructured":"Wu, C., Cao, L., Ge, Y., Liu, Y., Zhang, M., and Su, J. (March, January 22). A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, Virtually.","key":"ref_44"},{"unstructured":"Bai, H., and Zhao, H. (2018, January 20\u201326). Deep Enhanced Representation for Implicit Discourse Relation Recognition. Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, NM, USA.","key":"ref_45"},{"doi-asserted-by":"crossref","unstructured":"Lin, Y., Shen, S., Liu, Z., Luan, H., and Sun, M. (2016, January 7\u201312). Neural relation extraction with selective attention over instance. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany.","key":"ref_46","DOI":"10.18653\/v1\/P16-1200"},{"unstructured":"(2023, July 17). Jimmy Wales Wikimedia Community. Available online: https:\/\/en.wiktionary.org\/wiki\/Wiktionary:Main_Page.","key":"ref_47"},{"key":"ref_48","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume":"Volume 1","author":"Devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL \u201919)"},{"unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv.","key":"ref_49"},{"unstructured":"Ashish Vaswani, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Advances in Neural Information Processing Systems, NeurIPS.","key":"ref_50"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1162\/tacl_a_00142","article-title":"One Vector is Not Enough: Entity-Augmented Distributed Semantics for Discourse Relations","volume":"3","author":"Ji","year":"2015","journal-title":"Trans. Assoc. Comput. Linguist."},{"unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR, San Diego, CA, USA.","key":"ref_52"},{"doi-asserted-by":"crossref","unstructured":"Lei, W., Wang, X., Liu, M., Ilievski, I., He, X., and Kan, M.-Y. (2017, January 19\u201325). SWIM: A simple word interaction model for implicit discourse relation recognition. Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI \u201917), Melbourne, Australia.","key":"ref_53","DOI":"10.24963\/ijcai.2017\/562"},{"doi-asserted-by":"crossref","unstructured":"Varia, S., Hidey, C., and Chakrabarty, T. (2019, January 11\u201313). Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks. Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL \u201919), Stockholm, Sweden.","key":"ref_54","DOI":"10.18653\/v1\/W19-5951"},{"unstructured":"Kishimoto, Y., Murawaki, Y., and Kurohashi, S. (2020, January 11\u201316). Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives. Proceedings of the 12th Language Resources and Evaluation Conference (LREC \u201920), Marseille, France.","key":"ref_55"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1109\/TASLP.2021.3096041","article-title":"Learning Context-Aware Convolutional Filters for Implicit Discourse Relation Classification","volume":"29","author":"Munir","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/9\/1294\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:46:05Z","timestamp":1760129165000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/9\/1294"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":56,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["e25091294"],"URL":"https:\/\/doi.org\/10.3390\/e25091294","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2023,9,4]]}}}