In this work, we present an approach for informing clinical summarization models of ontological information. This is accomplished by providing an encoding of ontological terms matched in the original text as an additional feature to guide the deco...
In this work, we presented an approach for using weak supervision to train neural IR models. We showed that news articles can provide effective weak signals for some models—namely the models that use larger convolutional kernels. We discussed chal...
Credentials & highlights
- Project Views