检索结果-内蒙古大学图书馆

13th International Conference on Natural Language Processing and Chinese Computing

作者： Zheng, Ziwei Liang, Chao Xiang, Wei Wang, Bang Huazhong Univ Sci & Technol Sch Elect Informat & Commun Hubei Key Lab Smart Internet Technol Luoyu Rd 1037 Wuhan 430074 Hubei Peoples R China Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan Peoples R China

ISBN: (纸本)9789819794300;9789819794317

implicit discourse relation recognition (IDRR) is a challenging but vital task in discourse analysis that focuses on identifying and classifying the relation between two arguments without explicit connectives. Previous research has focused on constructing sophisticated argument representations or utilizing labels' hierarchical information while neglecting the intrinsic prior relational bias, where some relation categories are significantly less frequent than others due to inherent linguistic properties. Furthermore, some works amalgamate Explicit discourse relation recognition (EDRR) data with IDRR data to achieve data augmentation;however, the linguistic discrepancies between EDRR and IDRR data may mislead the relation recognition process. To address the prior relation bias and misleading from linguistic discrepancies, we propose a novel Bias-REctified Multi-way Learning (BREM) model, which incorporates prior probability knowledge to assist in understanding the discourse relations and employs a PLM-based method for pre-training on the EDRR dataset to achieve data augmentation without introducing misleading effects. Experiments on the PDTB 3.0 corpus show that BREM outperforms previous models, especially in identifying less frequent relation senses, highlighting the effectiveness of our proposed model. The source code of our proposed model is publicly available at https://***/zzzziwy/NLPCC2024-BREM_for_IDRR.

关键词： implicit discourse relation recognition prior relation bias Data Augmentation

来源：评论

学校读者我要写书评

暂无评论

Learning to Differentiate Pairwise-Argument Representations for implicit discourse relation recognition 24

Learning to Differentiate Pairwise-Argument Representations ...

引用

33rd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Wang, Zhipang Hong, Yu Lu, Yuxiang Zhou, Xiabing Yao, Jianmin Zhou, Guodong Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China

ISBN: (纸本)9798400704369

Recognizing implicit discourse relations between texts is challenging due to the absence of explicit connectives. Therefore, encoding texts into distinguishable semantic representations is crucial for connective-free relation determination. To enable encoders to produce clearly distinguishable representations, we propose a joint learning framework. It combines prototypical and adversarial learning as well as hub-migration based redistribution. We experiment on the openly-shared benchmark corpora PDTB 2.0, PDTB 3.0 and CoNLL-2016. The test results show that our methods yield substantial improvements, compared to BERT, RoBERTa and DeBERTa baselines. In a separate comparison experiment where implicit connectives are disable during training, our models outperform the previous work for the four main discourse relation types (Temporality, Comparison, Contingency and Expansion), achieving F1-scores of about 60.75%, 63.48%, 75.70% and 77.09%. On the other hand, our models obtain comparable performance compared to part of the state-of-the-art models which adopt implicit connectives as observable hints for training. When the pretrained language models are used as the backbones, our methods yield the extra time consumption, which is about 1 hour at worst when training is conducted on Tesla 40GB A100 GPU.

关键词： implicit discourse relation recognition Distinguishable Representation Joint Learning Framework Prototypical Learning Adversarial Learning Hub-migration Based Redistribution

来源：评论

学校读者我要写书评

暂无评论

Improving implicit discourse relation recognition via Connective Prediction and Dependency-weighted Label Hierarchy

Improving Implicit Discourse Relation Recognition via Connec...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Liu, Xianzhi Guo, Shaoru Li, Juncai Yan, Zhichao Su, Xuefeng Ma, Boxiang Wang, Yuzhi Li, Ru Shanxi Univ Sch Comp & Informat Technol Taiyuan Shanxi Peoples R China Shanxi Univ Inst Intelligent Informat Proc Taiyuan Shanxi Peoples R China

ISBN: (纸本)9798350359329;9798350359312

implicit discourse relation recognition aims to identify logical relations between two arguments without explicit connectives and is a challenging task in discourse analysis. Recent methods tend to leverage the label hierarchy to enhance discourse relation representations. However, they fail to fully utilize the connective information. Specifically, the methods overlook the guiding role of connectives in discourse relation classification by treating them as the last-level labels in the label hierarchy to leverage connective information, whereas it would be more appropriate to exploit connective information prior to relation classification. Moreover, these methods ignore the dependency degree of labels between different levels in the label hierarchy. In other words, they consider the label hierarchy as an unweighted undirected graph, and assume that the path weights between high-level labels and their corresponding low-level labels are the same, which leads to an insufficient construction of the label hierarchy. To overcome these issues, we propose a method for implicit discourse relation recognition (IDRR) utilizing Connective Prediction and Dependency-weighted Label Hierarchy (CP-DLH). Experimental results on PDTB 2.0 dataset show that our model achieves the state-of-the-art performance at all hierarchical levels.

关键词： implicit discourse relation recognition connective information label hierarchy

来源：评论

学校读者我要写书评

暂无评论

Interactive Capsule Networks with a Novel Dynamic Routing Mechanism for implicit discourse relation recognition

Interactive Capsule Networks with a Novel Dynamic Routing Me...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xu, Jing He, Ruifang Zhao, Haodong Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China

ISBN: (纸本)9781665488679

implicit discourse relation recognition aims to understand and infer the relations between discourse arguments, which is a classification task. Existing models mostly model the interaction of discourse arguments from the perspective of a single relation, which may fail to learn the complicated interaction patterns between two arguments under different discourse relations. In this paper, we propose a novel neural approach based on capsule networks with dynamic interactive routing mechanism, named Interactive Capsule Networks (ICN) model to address the issues. It dynamically maps argument feature capsules to discourse relation capsules in an iterative refinement manner, which can mine the discourse relation-indicative semantic clues of argument features. Then, the designed dynamic interactive routing mechanism captures the more comprehensive argument interaction from the perspective of multiple relations. The experimental results on the Penn discourse TreeBank (PDTB) demonstrate the effectiveness of our proposed ICN model.

关键词： implicit discourse relation recognition interaction patterns dynamic interactive routing mechanism

来源：评论

学校读者我要写书评

暂无评论

Conditional-Balanced Adversarial Delta Tuning for Cross-Domain implicit discourse relation recognition

Conditional-Balanced Adversarial Delta Tuning for Cross-Doma...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Chang Sun, HaoWen Zhao, Haodong He, Ruifang He, Xu Wang, Bo College of intelligence and Computing Tianjin University Tianjin China

ISBN: (纸本)9798350368741

implicit discourse relation recognition (IDRR) is faced with a domain dilemma. Recent studies have achieved breakthroughs in standard datasets, while they are not appropriate in domains with insufficient data, such as bio-medicine. In this paper, we treat this problem as a cross-domain IDRR task, which transfers knowledge from the source domain to improve the understanding of the target domain. However, cross-domain IDRR is supervised and suffers from striking domain gaps, and general domain adaptation methods are not applicable. Therefore, we propose a Conditional-Balanced Adversarial Delta Tuning (CBADT) framework, which 1) leverages delta tuning to mine the dense domain-specific knowledge in low-resource scenarios;2) builds a conditional adversarial verbalizer to inject domain-invariant knowledge into soft prompts;3) proposes a domain label fusion method to balance domain-specific label words and fit the hybrid features from two domains. Experiments on both Chinese and English corpora demonstrate the transferability of our model. © 2025 IEEE.

关键词： Domain Adaptation implicit discourse relation recognition Prompt Learning

来源：评论

学校读者我要写书评

暂无评论

Numerical Semantic Modeling for implicit discourse relation recognition 48

Numerical Semantic Modeling for Implicit Discourse Relation ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Chenxu Jian, Ping Wang, Hai Beijing Institute of Technology Department of Computer Science and Technology Beijing100081 China

ISBN: (纸本)9781728163277

implicit discourse relation recognition (IDRR), which infers discourse logical relations without the help of explicit connectives, is the bottleneck of discourse parsing. It is also an effective mean to test how well the natural language understanding models grasp the logical semantics of the text. Unfortunately, as an important part of text logical semantics, numerical logic has not been paid any attention to in the community. In this work, we attach importance to numerical semantics and design a numerical logic reasoning module specifically for the numeric tokens in discourse arguments to enhance the discourse logic inferring. Graph neural network is utilized here to calculate the interactions of these numerical elements by self-attention and inter-attention according to their numerical type and their location in the discourse arguments. Experimental results show that our model outperforms the baseline 1.36 % F1 score on the PDTB2.0 dataset. © 2023 IEEE.

关键词： graph neural networks implicit discourse relation recognition numerical logic reasoning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Prompt Learning With Distilled Connective Knowledge for implicit discourse relation recognition

引用

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2025年 33卷 586-597页

作者： Wang, Bang Wang, Zhenglin Xiang, Wei Mo, Yijun Huazhong Univ Sci & Technol HUST Sch Software Engn Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol HUST Hubei Key Lab Smart Internet Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan 430079 Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430074 Peoples R China

implicit discourse relation recognition (IDRR) aims at recognizing the discourse relation between two text segments without an explicit connective. Recently, prompt learning has been applied to the IDRR task with great performance improvements over various neural network-based approaches. However, the discrete nature of the state-art-of-art prompting approach requires manual design of templates and answers, a big hurdle for its practical applications. In this paper, we propose a continuous version of prompt learning together with connective knowledge distillation, called AdaptPrompt, to reduce manual design efforts via continuous prompting while further improving performance via knowledge transfer. In particular, we design and train a few virtual tokens to form continuous templates and automatically select the most suitable one by gradient search in the embedding space. We also design an answer-relation mapping rule to generate a few virtual answers as the answer space. Furthermore, we notice the importance of annotated connectives in the training dataset and design a teacher-student architecture for knowledge transfer. Experiments on the up-to-date PDTB Corpus V3.0 validate our design objectives in terms of the better relation recognition performance over the state-of-the-art competitors.

关键词： Training Encoding Adaptation models Text recognition Knowledge engineering Feature extraction Bidirectional control Annotations Vocabulary Vectors Continuous template implicit discourse relation recognition knowledge distillation prompt learning

来源：评论

学校读者我要写书评

暂无评论

Meta-learning based instance manipulation for implicit discourse relation recognition

引用

KNOWLEDGE-BASED SYSTEMS 2023年第1期267卷

作者： Zeng, Jiali Xie, Binbin Wu, Changxing Yin, Yongjing Zeng, Hualin Su, Jinsong Xiamen Univ Sch Informat Xiamen 361005 Fujian Peoples R China East China Jiaotong Univ Sch Software Nanchang 330013 Jiangxi Peoples R China

Without discourse connectives, implicit discourse relations recognition (IDRR) remains a challenging task and has attracted increasing attention. However, most studies ignore the issues of class imbalance and data noise. To alleviate these two problems, in this paper, we propose to improve the robustness of IDRR models with two novel meta-learning based instance manipulation networks: Meta-Weight-Net (MW-Net) and Meta-Label-Net (ML-Net), which adaptively control the effect of training instances and smooth the label distributions during model training, respectively. Specifically, we use MW-Net to adaptively learn an instance weight function directly from data and integrates the instance weights into the objective function of IDRR. Meanwhile, we adopt ML-Net to dynamically refine the label distributions, leading to the smaller variance in updating gradients. We conduct experiments on the PDTB 2.0 corpus. Experimental results and in-depth analysis empirically demonstrate the effectiveness of our networks.(c) 2023 Elsevier B.V. All rights reserved.

关键词： implicit discourse relation recognition Meta learning Class imbalance Instance weight

来源：评论

学校读者我要写书评

暂无评论

implicit discourse relation recognition via a BiLSTM-CNN Architecture With Dynamic Chunk-Based Max Pooling

引用

IEEE ACCESS 2019年 7卷 169281-169292页

作者： Guo, Fengyu He, Ruifang Dang, Jianwu Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China Japan Adv Inst Sci & Technol Sch Informat Sci Nomi Ishikawa 9231292 Japan

implicit discourse relation recognition is a serious challenge in discourse analysis, which aims to understand and annotate the latent relations between two discourse arguments, such as temporal and comparison. Most neural network-based models encode linguistic features (such as syntactic parsing and position information) as embedding vectors, which are prone to error propagation due to unsuitable pre-processing. Other methods apply different attention or memory mechanisms, mainly considering the key points in the discourse, yet ignore some valuable clues. In particular, those using convolution neural networks retain local contexts but lose word order information due to the standard pooling operation. The methods that use bidirectional long short-term memory network consider the word sequence and retain the global information, but cannot capture the context with different range sizes. In this paper, we propose a novel Dynamic Chunk-based Max Pooling BiLSTM-CNN framework (DC-BCNN) to address these issues. First, we exploit BiLSTMs to capture the semantic representations of discourse arguments. Second, we adopt the proposed convolutional layer to automatically extract the multi-granularity features (just like n-gram) by setting different convolution filter sizes. Then, we design a dynamic chunk-based max pooling strategy to obtain the important scaled features of different parts in one discourse argument. This strategy can dynamically divide each argument into several segments (called chunks) according to the argument length and the number of current pooling layer in the CNN and then select the maximum value of each chunk to indicate crucial information. We further utilize a fully connected layer with a softmax function to recognize discourse relations. The experimental results on two corpora (i.e., PDTB and HIT-CDTB) show that our proposed model is effective in implicit discourse relation recognition.

关键词： Semantics Task analysis Feature extraction Convolutional neural nets Logic gates Recurrent neural networks implicit discourse relation recognition discourse argument representation dynamic chunk-based max pooling BiLSTM CNN

来源：评论

学校读者我要写书评

暂无评论

Mental Imagery-Driven Neural Network to Enhance Representation for implicit discourse relation recognition 29th

Mental Imagery-Driven Neural Network to Enhance Representati...

引用

29th International Conference on Artificial Neural Networks (ICANN)

作者： Wang, Jian He, Ruifang Guo, Fengyu Han, Yugui Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China Tianjin Key Lab Cognit Comp & Applicat Tianjin Peoples R China

ISBN: (纸本)9783030616168;9783030616151

implicit discourse relation recognition is an important subtask in discourse parsing, which needs to infer the relation based on proper discourse comprehension. Recent studies on cognitive learning strategies have suggested that using mental imagery strategy will foster text comprehension, which could effectively improve the capability of learners' reading. Therefore, we propose a novel Mental Imagery-driven Neural Networks (MINN) to enhance representation for implicit discourse relation recognition. It employs the multi-granularity imagery vectors generated by the arguments to capture the deeper semantic information of discourse at different scales. Specifically, we 1) encode the different granularities of arguments (i.e., phrases, sentences.) and generate the corresponding imagery vectors as mentally imagining images of text content;2) fuse the argument representations and imagery vectors as sequence representations;3) further adopt self-attention to mine the important interactions between the sequence representations to infer the discourse relations. Extensive experimental results on the Penn discourse TreeBank (PDTB) show that our model achieves competitive results against several state-of-the-art systems.

关键词： implicit discourse relation recognition Mental imagery-driven neural network Self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：