2 papers
cs.CL2019
Rethinking Self-Attention: Towards Interpretability in Neural Parsing
Khalil Mrini, Franck Dernoncourt, Quan Tran +3
Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is di…
cs.CL2019
Interpretable Structure-aware Document Encoders with Hierarchical Attention
Khalil Mrini, Claudiu Musat, Michael Baeriswyl +1
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentence…