GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction
This work improves cross-lingual transfer for relation and event extraction, which is important for multilingual NLP applications, but it is incremental as it builds on existing graph-based and attention methods.
The paper tackled the problem of cross-lingual relation and event extraction by addressing limitations of graph convolutional networks in modeling long-range dependencies in dependency trees, and proposed GATE, which outperformed three recent methods by a large margin on the ACE05 dataset across English, Chinese, and Arabic.
Recent progress in cross-lingual relation and event extraction use graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations such that models trained on one language can be applied to other languages. However, GCNs struggle to model words with long-range dependencies or are not directly connected in the dependency tree. To address these challenges, we propose to utilize the self-attention mechanism where we explicitly fuse structural information to learn the dependencies between words with different syntactic distances. We introduce GATE, a {\bf G}raph {\bf A}ttention {\bf T}ransformer {\bf E}ncoder, and test its cross-lingual transferability on relation and event extraction tasks. We perform experiments on the ACE05 dataset that includes three typologically different languages: English, Chinese, and Arabic. The evaluation results show that GATE outperforms three recently proposed methods by a large margin. Our detailed analysis reveals that due to the reliance on syntactic dependencies, GATE produces robust representations that facilitate transfer across languages.