A Detailed Analysis of Semantic Dependency Parsing with Deep Neural Networks

Sammanfattning: The use of Long Short Term Memory (LSTM) networks continues to yield better results in natural language processing tasks. One area which recently has seen significant improvements is semantic dependency parsing, where the current state-of-the-art model uses a multilayer LSTM combined with an attention-based scoring function to predict the dependencies. In this thesis the state of the art model is first replicated and then extended to include features based on syntactical trees, which was found to be useful in a similar model. In addition, the effect of part-of-speech tags is studied. The replicated model achieves a labeled F1 score of 93.6 on the in-domain data and 89.2 on the out-of-domain data on the DM dataset, which shows that the model is indeed replicable. Using multiple features extracted from syntactic gold standard trees of the DELPH-IN Derivation Tree (DT) type increased the labeled scores to 97.1 and 94.1 respectively, while the use of predicted trees of the Stanford Basic (SB) type did not improve the results at all. The usefulness of part-of-speech tags was found to be diminished in the presence of other features.