论文标题
AMR解析的图形分割和对齐的可区分放松
A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing
论文作者
论文摘要
抽象含义表示（AMR）是一种宽覆盖的语义形式主义，代表句子含义为有向的无环图。要训练大多数AMR解析器，需要将图形分割为子图，并将每个这样的子图与句子中的一个单词对齐；这通常是在预处理中依靠手工制作的规则进行的。相反，我们将对齐和分割视为模型中的潜在变量，并将其作为端到端培训的一部分。 由于对结构化的潜在变量的边缘化是不可行的，因此我们使用变异自动编码框架。 为了确保端到端可区分优化，我们引入了分割和对齐问题的可区分放松。我们观察到，使用“贪婪”分割启发式启发式，诱导分割会产生可观的收益。我们方法的性能还涉及一个依赖\ citet {lyu-titov-2018-amr}的分割规则的模型，该模型是手工制作以处理单个AMR构造的。
Abstract Meaning Representations (AMR) are a broad-coverage semantic formalism which represents sentence meaning as a directed acyclic graph. To train most AMR parsers, one needs to segment the graph into subgraphs and align each such subgraph to a word in a sentence; this is normally done at preprocessing, relying on hand-crafted rules. In contrast, we treat both alignment and segmentation as latent variables in our model and induce them as part of end-to-end training. As marginalizing over the structured latent variables is infeasible, we use the variational autoencoding framework. To ensure end-to-end differentiable optimization, we introduce a differentiable relaxation of the segmentation and alignment problems. We observe that inducing segmentation yields substantial gains over using a `greedy' segmentation heuristic. The performance of our method also approaches that of a model that relies on the segmentation rules of \citet{lyu-titov-2018-amr}, which were hand-crafted to handle individual AMR constructions.
