arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.13210cs.CLcs.LG
收藏

基于图卷积网络的框架语义语义解析句法构成路径编码

Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks

Heriot-Watt University(赫瑞-瓦特大学)

Emanuele Bastianelli, Andrea Vanzo, Oliver Lemon

摘要:

我们研究的问题,从选区树的句法信息集成到一个神经模型中的框架语义解析的子任务,即目标识别(TI),框架识别(FI),和语义角色标注(SRL)。我们使用图卷积网络来学习成分的特定表示,使得每个成分被描述为它对应的产生式语法规则。我们利用这些表示来构建句子中每个单词的句法特征,计算为单词和树中特定任务节点之间路径上的所有成分的总和,例如SRL的目标谓词。当在FrameNet 1.5上测试时,我们的方法在TI和SRL上分别提高了约1%和约3.5%的最新结果(以BERT作为输入获得了+2.5%的额外点),同时在CoNLL 05数据集上产生了与其他语法感知系统相当的结果。

英文摘要:

We study the problem of integrating syntactic information from constituency trees into a neural model in Frame-semantic parsing sub-tasks, namely Target Identification (TI), FrameIdentification (FI), and Semantic Role Labeling (SRL). We use a Graph Convolutional Network to learn specific representations of constituents, such that each constituent is profiled as the production grammar rule it corresponds to. We leverage these representations to build syntactic features for each word in a sentence, computed as the sum of all the constituents on the path between a word and a task-specific node in the tree, e.g. the target predicate for SRL. Our approach improves state-of-the-art results on the TI and SRL of ~1%and~3.5% points, respectively (+2.5% additional points are gained with BERT as input), when tested on FrameNet 1.5, while yielding comparable results on the CoNLL05 dataset to other syntax-aware systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑