A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

Word analogy test file to evaluate Italian embeddings.

Trip-MAML is a Multi-Aspect Multi-Lingual dataset for aspect-oriented opinion mining annotated at the sentence-level, consisting of Tripadvisor hotel reviews in English, Italian, and Spanish.

Code of the paper Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

Graph to sequence implemented in Pytorch combining Graph convolutional networks and opennmt-py

this is the code used in the paper "Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations"