Few Shot Learning for Information Verification
This work addresses the problem of information verification for applications requiring complex evidence integration, presenting an incremental improvement over previous methods that simply concatenated evidence.
The paper tackles the challenge of verifying claims by selecting and integrating hierarchical evidence from Wikipedia articles, achieving effective fact verification with minimal additional training using a graph-based attention and convolution approach.
Information verification is quite a challenging task, this is because many times verifying a claim can require picking pieces of information from multiple pieces of evidence which can have a hierarchy of complex semantic relations. Previously a lot of researchers have mainly focused on simply concatenating multiple evidence sentences to accept or reject claims. These approaches are limited as evidence can contain hierarchical information and dependencies. In this research, we aim to verify facts based on evidence selected from a list of articles taken from Wikipedia. Pretrained language models such as XLNET are used to generate meaningful representations and graph-based attention and convolutions are used in such a way that the system requires little additional training to learn to verify facts.