• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
Advanced Search
Yao Hao, Xiong Jinghui, Li Chunsheng, Wu Changxing. Implicit Discourse Relation Recognition Based on Multi-Granularity Information Interaction and Data Augmentation[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202440511
Citation: Yao Hao, Xiong Jinghui, Li Chunsheng, Wu Changxing. Implicit Discourse Relation Recognition Based on Multi-Granularity Information Interaction and Data Augmentation[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202440511

Implicit Discourse Relation Recognition Based on Multi-Granularity Information Interaction and Data Augmentation

More Information
  • Author Bio:

    Yao Hao: born in 1999. Master candidate. His main research interest is nature language processing, with a focus on discourse analysis

    Xiong Jinghui: born in 1999. Master candidate. His main research interest is nature language processing, with a focus on discourse analysis.(409119311@qq.com)

    Li Chunsheng: born in 1980. Associate professor of engineering. His research interests include information retrieval.(lcs_2002@163.com)

    Wu Changxing: born in 1981. PhD, associate professor. Member of CCF. His research interests include nature language processing and information retrieval. (wuchangxing@ecjtu.edu.cn)

  • Received Date: June 10, 2024
  • Accepted Date: January 25, 2025
  • Available Online: January 25, 2025
  • Implicit discourse relation recognition aims at automatically identifying semantic relations (such as Comparison) between two arguments (sentence or clause) in the absence of explicit connectives. Existing methods have confirmed that the introduction of phrase information can effectively boost the performance. However, there are still the following shortcomings: 1) These models typically rely on syntactic parsers and do not fully capture the interactions between words, phrases, and arguments. 2) The problem of data sparsity often occurs during training when incorporating the phrase information. To address the above issues, we propose an implicit discourse relation recognition model based on multi-granularity information interaction (MGII) and develop a chain decoding-inspired data augmentation method (DAM). Specifically, our proposed model is designed to automatically acquire semantic representations of n-grams using a stacked convolutional neural network. It then explicitly models the interactions between words, phrases and arguments based on Transformer layers and ultimately predicts multi-level discourse relationships in a chain-decoding way. Our data augmentation method simultaneously pretrains both the encoding and decoding modules, enabling the effective utilization of massive explicit discourse data, which are naturally annotated by connectives, to mitigate the issue of data sparsity. The proposed method significantly outperforms recent benchmark models on the PDTB datasets. Furthermore, it does not rely on syntactic parsers, demonstrating strong applicability.

  • [1]
    Wang Chang, Wang Bang. An end-to-end topic-enhanced self-attention network for social emotion classification[C]// Proc of the Web Conf 2020. New York: ACM, 2020: 2210–2219
    [2]
    Li Huifeng, Srihari R, Niu Cheng, et al. Location normalization for information extraction[C/OL]// Proc of the 19th Int Conf on COLING. Stroudsburg, PA: ACL, 2002[2024-01-03]. https://aclanthology.org/C02-1127/
    [3]
    Cohan A, Dernoncourt F, Kim D, et al. A discourse-aware attention model for abstractive summarization of long documents[C]// Proc of the 2018 Conf of NAACL: Human Language Technologies. Stroudsburg, PA: ACL, 2018: 615–621
    [4]
    Verberne S, Boves L, Oostdijk N, et al. Evaluating discourse-based answer extraction for why -question answering[C]// Proc of the 30th Annual Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2007: 735–736
    [5]
    Chan C, Cheng Jiayang, Wang Weiqi, et al. ChatGPT evaluation on sentence level relations: A focus on temporal, causal, and discourse relations[C]// Proc of Findings of ACL: EACL 2024. Stroudsburg, PA: ACL, 2024: 684−721
    [6]
    Yung F, Ahmad M, Scholman M, et al. Prompting implicit discourse relation annotation[C]// Proc of The 18th Linguistic Annotation Workshop. Stroudsburg, PA: ACL, 2024: 150–165
    [7]
    Ruan Huibin, Hong Yu, Xu Yang, et al. Interactively-propagative attention learning for implicit discourse relation recognition[C]// Proc of the 28th Int Conf on COLING. Stroudsburg, PA: ACL, 2020: 3168–3178
    [8]
    Liu Xin, Ou Jiefu, Song Yangqiu, et al. On the importance of word and sentence representation learning in implicit discourse relation classification[C]// Proc of the 29th IJCAI. San Francisco, CA: Morgan Kaufmann, 2020: 3830–3836
    [9]
    Ma Yuhao, Zhu Jian, Liu Jie. Enhanced semantic representation learning for implicit discourse relation classification[J]. Applied Intelligence, 2022, 52(7): 7700−7712 doi: 10.1007/s10489-021-02785-6
    [10]
    Xiang Wei, Wang Bang, Dai Lu, et al. Encoding and fusing semantic connection and linguistic evidence for implicit discourse relation recognition[C]// Proc of Findings of ACL: ACL 2022. Stroudsburg, PA: ACL: 2022, 3247–3257
    [11]
    Wang Yizhong, Li Sujian, Yang Jingfeng, et al. Tag-enhanced tree-structured neural networks for implicit discourse relation classification[C]// Proc of the 8th IJNLP. Stroudsburg, PA: ACL, 2017: 496–505
    [12]
    王秀利 ,金方焱. 融合特征编码和短语交互感知的隐式篇章关系识别[J]. 电子学报,2024,52(4):1377-1388

    Wang Xiuli , Jin Fangyan. Implicit discourse relation recognition integrating feature coding and phrase interaction perception[J]. Acta Electronica Sinica, 2024, 52(4): 1377-1388 (in Chinese)
    [13]
    Liu Yang, Li Sujian, Zhang Xiaodong, et al. Implicit discourse relation classification via multi-task neural networks[C]// Proc of the 30th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2016: 2750–2756
    [14]
    Kishimoto Y,Murawaki Y,Kurohashi S. Adapting BERT to implicit discourse relation classification with a focus on discourse connectives[C]// Proc of LREC 2020. Paris:ELRA,2020:1152–1158
    [15]
    Zhang Biao,Su Jinsong,Xiong Deyi,et al. Shallow convolutional neural network for implicit discourse relation recognition[C]// Proc of the 2015 Conf on EMNLP. Stroudsburg,PA:ACL,2015:2230–2235
    [16]
    Rutherford A, Demberg V, Xue Nianwen. A systematic study of neural discourse models for implicit discourse relation[C]// Proc of the 15th Conf of EACL. Stroudsburg, PA: ACL, 2017: 281–291
    [17]
    Chen Jifan, Zhang Qi, Liu Pengfei, et al. Implicit discourse relation detection via a deep architecture with gated relevance network[C]// Proc of the 54th Annual Meeting of the ACL. Stroudsburg, PA: ACL, 2016: 1726–1735
    [18]
    Liu Yang, Li Sujian. Recognizing Implicit discourse relations via repeated reading: Neural networks with multi-level attention[C]// Proc of the 2016 Conf on EMNLP. Stroudsburg, PA: ACL, 2016: 1224–1233
    [19]
    Lei Wenqiang, Wang Xuancong, Liu Meichun, et al. SWIM: A simple word interaction model for implicit discourse relation recognition[C]// Proc of the 26th IJCAI. San Francisco, CA: Morgan Kaufmann, 2017: 4026–4032
    [20]
    Wu Changxing, Cao Liuwen, Ge Yubin, et al. A label dependence-aware sequence generation model for multi-level implicit discourse relation recognition[C]// Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2022, 11486–11494
    [21]
    Long Wanqiu, Webber B. Facilitating contrastive learning of discourse relational senses by exploiting the hierarchy of sense relations[C]// Proc of the 2022 Conf on EMNLP. Stroudsburg, PA: ACL, 2022: 10704–10716
    [22]
    Jiang Yuxin, Zhang Linhan, Wang Wei. Global and local hierarchy-aware contrastive framework for implicit discourse relation recognition[C]// Proc of Findings of ACL: ACL 2023. Stroudsburg, PA: ACL, 2023: 8048–8064
    [23]
    Xiang Wei, Wang Zhenglin, Dai Lu, et al. ConnPrompt: connective-cloze prompt learning for implicit discourse relation recognition[C]// Proc of the 29th Int Conf on COLING. Stroudsburg, PA: ACL, 2022: 902–911
    [24]
    Zhou Hao, Lan Man, Wu Yuanbin, et al. Prompt-based connective prediction method for fine-grained implicit discourse relation recognition[C]// Proc of Findings of ACL: EMNLP 2022. Stroudsburg, PA: ACL, 2022: 3848–3858
    [25]
    Zhao Haodong, He Ruifang, Xiao Mengnan, et al. Infusing hierarchical guidance into prompt tuning: a parameter-efficient framework for multi-level implicit discourse relation recognition[C]// Proc of the 61st Annual Meeting of ACL. Stroudsburg, PA: ACL, 2022, 2023: 6477–6492
    [26]
    Wu Hongyi, Zhou Hao, Lan Man, et al. Connective prediction for implicit discourse relation recognition via knowledge distillation[C]// Proc of the 61st Annual Meeting of ACL. Stroudsburg, PA: ACL, 2023: 5908–5923
    [27]
    Liu Wei, Strube M. Annotation-inspired implicit discourse relation classification with auxiliary discourse connective generation[C]// Proc of the 61st Annual Meeting of ACL. Stroudsburg, PA: ACL, 2023: 15696–15712
    [28]
    Wu Changxing, Shi Xiaodong, Chen Yidong, et al. Improving implicit discourse relation recognition with discourse-specific word embeddings[C]// Proc of the 55th Annual Meeting of ACL. Stroudsburg, PA: ACL, 2017: 269–274
    [29]
    Ru Dongyu, Qiu Lin, Qiu Xipeng, et al. Distributed marker representation for ambiguous discourse markers and entangled relations[C]// Proc of the 61st Annual Meeting of ACL. Stroudsburg, PA: ACL, 2023: 5334–5351
    [30]
    Wang Chenxu, Jian Ping, Huang Mu. Prompt-based logical semantics enhancement for implicit discourse relation recognition[C]// Proc of the 2023 Conf on EMNLP, 2023: 687–699
    [31]
    范伟,刘勇. 基于时空Transformer的社交网络信息传播预测[J]. 计算机研究与发展,2022,59(8):1757−1769 doi: 10.7544/issn1000-1239.20220064

    Fan Wei, Liu Yong. Social network information diffusion prediction based on spatial-temporal transformer[J]. Journal of Computer Research and Development, 2022, 59(8): 1757−1769 (in Chinese) doi: 10.7544/issn1000-1239.20220064
    [32]
    Rashmi P, Nikhil D, Alan L, et al. The penn discourse TreeBank 2.0[C]// Proc of the 6th Int Conf on LREC. Stroudsburg, PA: ACL, 2008: 2961–2968
    [33]
    Webber B, Prasad R, Lee A, et al. The penn discourse TreeBank 3.0 annotation manual[R]. Philadelphia, PA: University of Pennsylvania, 2019
    [34]
    Ji Yangfeng, Eisenstein J. One vector is not enough: entity-augmented distributed semantics for discourse relations[J]. Transactions of the Association for Computational Linguistics 2015, 3: 329−344. https://doi.org/10.1162/tacl_a_00142
    [35]
    Liu Yinhan, Ott M, Goyal N, et al. RoBERTa: A robustly optimized BERT pretraining approach[J]. arXiv preprint, arXiv: 1907.11692, 2019
    [36]
    Sileo D Van-De-Cruys T, Pradel C, et al. Mining discourse markers for unsupervised sentence representation learning[C]// Proc of the 2019 Conf of NAACL: Human Language Technologies. Stroudsburg, PA: ACL, 2019: 3477–3486
  • Related Articles

    [1]Attention-enhanced Semantic Fusion Knowledge Graph Representation Learning Framework[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202440669
    [2]Ke Jing, Xie Zheyong, Xu Tong, Chen Yuhao, Liao Xiangwen, Chen Enhong. An Implicit Semantic Enhanced Fine-Grained Fake News Detection Method Based on Large Language Models[J]. Journal of Computer Research and Development, 2024, 61(5): 1250-1260. DOI: 10.7544/issn1000-1239.202330967
    [3]Zhang Wenhan, Liu Xiaoming, Yang Guan, Liu Jie. Cross-Domain Named Entity Recognition of Multi-Level Structured Semantic Knowledge Enhancement[J]. Journal of Computer Research and Development, 2023, 60(12): 2864-2876. DOI: 10.7544/issn1000-1239.202220413
    [4]Qi Peng, Cao Juan, Sheng Qiang. Semantics-Enhanced Multi-Modal Fake News Detection[J]. Journal of Computer Research and Development, 2021, 58(7): 1456-1465. DOI: 10.7544/issn1000-1239.2021.20200804
    [5]Wu Famin, Lü Guangyi, Liu Qi, He Ming, Chang Biao, He Weidong, Zhong Hui, Zhang Le. Deep Semantic Representation of Time-Sync Comments for Videos[J]. Journal of Computer Research and Development, 2019, 56(2): 293-305. DOI: 10.7544/issn1000-1239.2019.20170752
    [6]Cheng Xiaoyang, Zhan Yongzhao, Mao Qirong, Zhan Zhicai. Video Semantic Analysis Based on Topographic Sparse Pre-Training CNN[J]. Journal of Computer Research and Development, 2018, 55(12): 2703-2714. DOI: 10.7544/issn1000-1239.2018.20170579
    [7]Yang Lin, Zhang Libo, Luo Tiejian, Wan Qiyang, Wu Yanjun. Knowledge Schematization Method Based on Link and Semantic Relationship[J]. Journal of Computer Research and Development, 2017, 54(8): 1655-1664. DOI: 10.7544/issn1000-1239.2017.20170177
    [8]Han Jun, Fan Ju, Zhou Lizhu. Semantic-Enhanced Spatial Keyword Search[J]. Journal of Computer Research and Development, 2015, 52(9): 1954-1964. DOI: 10.7544/issn1000-1239.2015.20140686
    [9]Ma Yuchi, Yang Ning, Xie Lin, Li Chuan, and Tang Changjie. Social Roles Discovery of Moving Objects Based on Spatial-Temporal Associated Semantics and Temporal Entropy of Trajectories[J]. Journal of Computer Research and Development, 2012, 49(10): 2153-2160.
    [10]Liu Yanan, Wu Fei, and Zhuang Yueting. Video Semantics Mining Using Multi-Modality Subspace Correlation Propagation[J]. Journal of Computer Research and Development, 2009, 46(1): 1-8.
  • Cited by

    Periodical cited type(3)

    1. 台建玮,杨双宁,王佳佳,李亚凯,刘奇旭,贾晓启. 大语言模型对抗性攻击与防御综述. 计算机研究与发展. 2025(03): 563-588 . 本站查看
    2. 布文茹,王昊,李晓敏,周抒,邓三鸿. 古诗词中的探赜索隐:决策层融合大模型修正的典故引用识别方法. 科技情报研究. 2024(04): 37-52 .
    3. 付志远,陈思宇,陈骏帆,海翔,石岩松,李晓琦,李益红,岳秋玲,张玉清. 大语言模型安全的挑战与机遇. 信息安全学报. 2024(05): 26-55 .

    Other cited types(0)

Catalog

    Article views (112) PDF downloads (19) Cited by(3)

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return