A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing
A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing
复制标题
DOI：
10.18653/v1/d19-1295
复制
发表时间：
2019-11
影响因子：
10.6
通讯作者：
Zeyu Dai;Ruihong Huang
中科院分区：
文献类型：
--
作者：
Zeyu Dai;Ruihong Huang
我们认为，外部常识知识和语言约束需要纳入神经网络模型，以减轻数据稀疏性问题，并进一步提高话语分析的性能。意识到外部知识和语言约束可能并不总是适用于理解一个特定的上下文，我们提出了一个正则化的方法，紧密结合这些约束与上下文派生词表示。同时，通过在目标函数中加入正则化项，平衡了上下文和约束的注意力。实验表明，我们的知识正则化方法优于所有以前的系统上的基准数据集PDTB的话语分析。
We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing. Realizing that external knowledge and linguistic constraints may not always apply in understanding a particular context, we propose a regularization approach that tightly integrates these constraints with contexts for deriving word representations. Meanwhile, it balances attentions over contexts and constraints through adding a regularization term into the objective function. Experiments show that our knowledge regularization approach outperforms all previous systems on the benchmark dataset PDTB for discourse parsing.