UMBC ebiquity
arXiv
SURFACE: Semantically Rich Fact Validation with Explanations
November 1, 2018
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 a 90% improvement over the state-of-the-art baseline in retrieving relevant sentences and a 70% relative improvement in classification.
