Working Memory-Driven Neural Networks with a Novel Knowledge Enhancement Paradigm for Implicit Discourse Relation Recognition
Working Memory-Driven Neural Networks with a Novel Knowledge Enhancement Paradigm for Implicit Discourse Relation Recognition
复制标题
DOI：
10.1609/aaai.v34i05.6287
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Fengyu Guo;Ruifang He;J. Dang;Jian Wang
中科院分区：
文献类型：
--
作者：
Fengyu Guo;Ruifang He;J. Dang;Jian Wang
语篇分析的目的是理解和推断两个语篇论元之间的潜在关系，如时间、比较等，识别隐含的语篇关系是一项具有挑战性的任务。目前的模型大多集中在基于学习的方法，只利用句子内的文本信息来识别语篇关系，忽略了更广泛的上下文以外的话语。此外，人们理解话语的意义和关系，严重依赖于他们相互关联的工作记忆（例如，即时记忆，长期记忆）。受此启发，我们提出了一个知识增强的注意神经网络（KANN）框架来解决这些问题。具体地说，它建立了一个相互注意矩阵来捕捉两个参数之间的相互信息，作为即时记忆。而论元中隐含的知识则是从外部知识源中提取，并编码为词间语义连接嵌入，进一步构建知识矩阵，作为长期记忆。我们设计了一个新的范式，通过两种方式，通过记忆的协作来丰富论元表征：1）将知识矩阵整合到相互注意矩阵中，将知识隐式映射到捕捉两个话语论元之间的不对称交互的过程中;（2）将论元表征与语义连接嵌入直接连接起来，明确地补充知识，帮助语篇理解。在PDTB上的实验结果也表明了KANN模型的有效性。
Recognizing implicit discourse relation is a challenging task in discourse analysis, which aims to understand and infer the latent relations between two discourse arguments, such as temporal, comparison. Most of the present models largely focus on learning-based methods that utilize only intra-sentence textual information to identify discourse relations, ignoring the wider contexts beyond the discourse. Moreover, people comprehend the meanings and the relations of discourses, heavily relying on their interconnected working memories (e.g., instant memory, long-term memory). Inspired by this, we propose a Knowledge-Enhanced Attentive Neural Network (KANN) framework to address these issues. Specifically, it establishes a mutual attention matrix to capture the reciprocal information between two arguments, as instant memory. While implicitly stated knowledge in the arguments is retrieved from external knowledge source and encoded as inter-words semantic connection embeddings to further construct knowledge matrix, as long-term memory. We devise a novel paradigm with two ways by the collaboration of the memories to enrich the argument representation: 1) integrating the knowledge matrix into the mutual attention matrix, which implicitly maps knowledge into the process of capturing asymmetric interactions between two discourse arguments; 2) directly concatenating the argument representations and the semantic connection embeddings, which explicitly supplements knowledge to help discourse understanding. The experimental results on the PDTB also show that our KANN model is effective.