SURFACE: Semantically Rich Fact Validation with Explanations
This addresses the challenge of fact-checking for applications like misinformation detection, though it is incremental as it builds on the existing FEVER task.
The paper tackled the problem of validating the veracity of sentences using Wikipedia as a source, and the result was a model that improved sentence retrieval by 90% and classification by 70% over the state-of-the-art on the FEVER dataset.
Judging the veracity of a sentence making one or more claims is an important and challenging problem with many dimensions. The recent FEVER task asked participants to classify input sentences as either SUPPORTED, REFUTED or NotEnoughInfo using Wikipedia as a source of true facts. SURFACE does this task and explains its decision through a selection of sentences from the trusted source. Our multi-task neural approach uses semantic lexical frames from FrameNet to jointly (i) find relevant evidential sentences in the trusted source and (ii) use them to classify the input sentence's veracity. An evaluation of our efficient three-parameter model on the FEVER dataset showed an improvement of 90% over the state-of-the-art baseline on retrieving relevant sentences and a 70% relative improvement in classification.