高级检索

    基于多粒度信息交互和数据增强的隐式篇章关系识别

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

    • 摘要: 隐式篇章关系识别旨在推导没有连接词的论元(句子或子句)之间的语义关系. 现有研究证实引入短语信息能切实提升识别性能,但依然存在以下不足:1)通常依赖句法分析器且词、短语与论元之间的交互不充分;2)引入短语信息导致的数据稀疏性问题. 为此,分别提出基于多粒度信息交互的隐式篇章关系识别模型MGII(multi-granularity information interaction)和基于链式解码的数据增强方法DAM (data augmentation method). 所提模型通过卷积神经网络自动学习n-gram短语的语义表示,利用Transformer层显式地建模词、短语和论元之间的交互,并通过链式解码进行多级篇章关系预测. 提出的数据增强方法同时预训练编码模块和解码模块,从而能有效地利用大量显式篇章关系数据. 所提方法在PDTB数据集上的性能显著优于近期的基准模型,且不依赖句法分析器,具有较强的适用性.

       

      Abstract: 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.

       

    /

    返回文章
    返回