AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation

arXiv:2311.09521v2 Announce Type: replace
Abstract: Ensuring factual consistency is crucial for natural language generation tasks, particularly in abstractive summarization, where preserving the integrity of information is paramount. Prior works on evaluating factual consistency of summarization often take the entailment-based approaches that first generate perturbed (factual inconsistent) summaries and then train a classifier on the generated data to detect the factually inconsistencies during testing time. However, previous approaches generating perturbed summaries are either of low coherence or lack error-type coverage. To …

abstract amr arxiv cs.cl evaluation generate information integrity language language generation natural natural language natural language generation negative prior samples summarization tasks train type