Our user studies confirm that the learned LEs are explainable and capture domain semantics.
Deep neural models achieve some of the best results for semantic role labeling.
Although different languages have different argument annotations, polyglot training, the idea of training one model on multiple languages, has previously been shown to outperform monolingual baselines, especially for low resource languages.
With negligible overhead in the number of parameters and training time, our Past Decode Regularization (PDR) method achieves a word level perplexity of 55. 6 on the Penn Treebank and 63. 5 on the WikiText-2 datasets using a single softmax.
Ranked #6 on Language Modelling on WikiText-2
We propose a general and effective improvement to the BiLSTM model which encodes each suffix and prefix of a sequence of tokens in both forward and reverse directions.
In many neural models, new features as polynomial functions of existing ones are used to augment representations.