Search Results for author:
Found 4 papers, 3 papers with code
Structural Guidance for Transformer Language Models
Here we study whether structural guidance leads to more human-like systematic linguistic generalization in Transformer language models without resorting to pre-training on very large amounts of data.
AMR Parsing with Action-Pointer Transformer
In this work, we propose a transition-based system that combines hard-attention over sentences with a target-side action pointer mechanism to decouple source tokens from node representations and address alignments.
Ranked #4 on
AMR Parsing
on LDC2020T02
(using extra training data)
From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities.
Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs.
Ranked #3 on
Part-Of-Speech Tagging
on Penn Treebank