End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs
This addresses the challenge of fully automated question answering for users needing seamless interaction with knowledge graphs, though it is incremental by extending existing differentiable methods.
The paper tackles the problem of integrating entity resolution into end-to-end question answering over knowledge graphs, eliminating the need for hand-annotated entities during training and runtime, and shows that the model performs close to baselines using hand-annotated entities on two public datasets.
Recently, end-to-end (E2E) trained models for question answering over knowledge graphs (KGQA) have delivered promising results using only a weakly supervised dataset. However, these models are trained and evaluated in a setting where hand-annotated question entities are supplied to the model, leaving the important and non-trivial task of entity resolution (ER) outside the scope of E2E learning. In this work, we extend the boundaries of E2E learning for KGQA to include the training of an ER component. Our model only needs the question text and the answer entities to train, and delivers a stand-alone QA model that does not require an additional ER component to be supplied during runtime. Our approach is fully differentiable, thanks to its reliance on a recent method for building differentiable KGs (Cohen et al., 2020). We evaluate our E2E trained model on two public datasets and show that it comes close to baseline models that use hand-annotated entities.