Weakly Supervised Dataset
Related Papers
DualTKB: A Dual Learning Bridge between Text and Knowledge Base
AbstractIn this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs). We investigate the impact of weak …...
End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs
AbstractRecently, 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 weakly supervised textual entailment approach to zero-shot text classification
AbstractZero-shot text classification is a widely studied task that deals with a lack of annotated data. The most common approach is to reformulate it as a textual entailment problem, enabling …...
WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction
AbstractMost existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness. Here, to mitigate the dependence on manual data, we broaden the source of …...