Papers by Maria Maleshkova

1 papers
Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks (2021.eacl-main)

Copied to clipboard

Challenge: Existing knowledge graphs are widely used for (complex) conversational question answering . LASAGNE improves the F1-score on eight out of ten question types .
Approach: They propose a multi-task neural semantic parsing approach for (complex) conversational question answering over a knowledge graph using a transformer model and a Graph Attention Networks model.
Outcome: The proposed approach outperforms baselines on eight out of ten question types on a standard dataset for complex sequential question answering.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations