Search Results for author:
Found 5 papers, 3 papers with code
Multimodal Phased Transformer for Sentiment Analysis
We evaluate our model with three sentiment analysis datasets and achieve comparable or superior performance compared with the existing methods, with a 90% reduction in the number of parameters.
On the Transition from Neural Representation to Symbolic Knowledge
Bridging the huge disparity between neural and symbolic representation can potentially enable the incorporation of symbolic thinking into neural networks from essence.
Graph Conditioned Sparse-Attention for Improved Source Code Understanding
The fusion between a graph representation like Abstract Syntax Tree (AST) and a source code sequence makes the use of current approaches computationally intractable for large input sequence lengths.
GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarization
SCG is the result of the early fusion between a source code snippet and the AST representation.
GN-Transformer: Fusing AST and Source Code information in Graph Networks
As opposed to natural languages, source code understanding is influenced by grammar relations between tokens regardless of their identifier name.
