范亚鑫,蒋峰,朱巧明,褚晓敏,李培峰. 融合全局和局部信息的汉语宏观篇章结构识别[J]. 中文信息学报, 2022, 36(3): 1-9.
FAN Yaxin, JIANG Feng, ZHU Qiaoming, CHU Xiaomin, LI Peifeng. Identification of Chinese Macro Discourse Structure with Global and Local Information. , 2022, 36(3): 1-9.
Identification of Chinese Macro Discourse Structure with Global and Local Information
FAN Yaxin1, JIANG Feng1, ZHU Qiaoming1,2, CHU Xiaomin1, LI Peifeng1,2
1.School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu 215006, China; 2.AI Research Institute, Soochow University, Suzhou, Jiangsu 215006, China
Abstract：The discourse structure recognition task aims to identify the structure between adjacent discourse units for a hierarchical discourse structure tree .This paper proposes a pointer network model that integrates global and local information. It can effectively improve the ability of macro text structure recognition by considering the global semantic information and the closeness of the semantic relationship between paragraphs. The experimental results in the Chinese macro discourse Treebank(MCDTB) show that the proposed model outperforms the state-of-the-art model.
[1] Maria L, Simon D, Shyamasree S, et al. A discourse-driven content model for summarising scientific articles evaluated in a complex question answering task[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2013:747-757. [2] Arman C, Nazli G. Scientific article summarization using citation-context and article's discourse structure[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2014:390-400. [3] 褚晓敏,奚雪峰,蒋峰,等.宏观篇章结构表示体系和语料建设[J].软件学报,2020,31(2):321-343. [4] Jiang F, Xu S, Chu X, et al. MCDTB: A Macro-level Chinese Discourse TreeBank[C]//Proceedings of the 27th International Conference on Computational Linguistics, 2018:3493-3504. [5] Jiang F, Li P, Chu X, et al. Recognizing macro Chinese discourse structure on label degeneracy combination model[C]//Proceedings of the 7th CCF International Conference on Natural Language Processing and Chinese Computing, 2018:92-104. [6] Zhou Y, Chu X, Li P, et al. Constructing Chinese macro discourse tree via multiple views and word pair similarity[C]//Proceedings of the 8th CCF International Conference on Natural Language Processing and Chinese Computing, 2019:773-786. [7] Carlson L, Okurowski M E, Marcu D. RST discourse treebank[M]. Linguistic Data Consortiumm, University of Pennsylvania, 2002. [8] Lin X, Shafiq J, Prathyusha J, et al. A unified linear-time framework for sentence-level discourse parsing[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019:4190-4200. [9] Van Dijk T A. Macrostructures: an interdisciplinary study of global structures in discourse, interaction, and cognition[M]. Hillsdale: Lawrence Erlbaum Associates, Inc., 1980. [10] Hugo H, Helmut P, David A D, et al. HILDA: a discourse parser using support vector machine classification[J]. Dialogue & Discourse, 2010, 1(3):1-33. [11] Shafiq J, Giuseppe C, Raymond N, et al.Combining intra-and multi-sentential rhetorical parsing for document-level discourse analysis[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 2013:486-496. [12] Ji Y, Jacob E. Representation learning for text-level discourse parsing[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014:13-24. [13] Caroline S, Alex L.Combining hierarchical clustering and machine learning to predict high-level discourse structure[C]//Proceedings of the 20th International Conference on Computational Linguistics,2004:43-49. [14] Sepp H, Jurgen S. Long short-term memory[J]. Neural Computation, 1997,9(8): 1735-1780. [15] Ashish V, Noam S, Niki P, et al. Attention is all you need[C]//Proceedings of the 31th Annual Conference on Neural Information Processing Systems, 2017:5998-6008. [16] Guo F, He R, Jin D, et al. Implicit discourse relation recognition using neural tensor network with interactive attention and sparse learning[C]//Proceedings of the 27th International Conference on Computational Linguistics, 2018:547-558. [17] 徐昇,王体爽,李培峰,等.运用多层注意力神经网络识别中文隐式篇章关系[J].中文信息学报, 2019, 33 (8): 12-19. [18] Ilya S, Oriol V, Quoc V L.Sequence to sequence learning with neural networks[C]//Proceedings of the 28th Annual Conference on Neural Information Processing Systems, 2014:3104-3112. [19] Oriol V, Meire F, Navdeep J. Pointer networks[C]//Proceedings of the 29th Annual Conference on Neural Information Processing Systems, 2015:2692-2700. [20] Chung J, Caglar G, Kyung H C, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv preprint arXiv: 1412,3555,2014. [21] Cho K, Bart V M, Caglar G, et al. Learning Phrase Representations using RNN encoder-decoder for statistical machinetranslation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2014:1724-1734. [22] Mathieu M, Philippe M, Nicholas Ar. How much progress have we made on RST discourse parsing? a replication study of recent results on the RST-DT[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017:1319-1324. [23] Tomas M, Ilya S, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 27th Annual Conference on Neural Information Processing Systems, 2013:3111-3119.
2022, Vol. 36 
