Factual Error Correction for Abstractive Summaries Using Entity Retrieval

TL;DR

This paper introduces RFEC, an efficient entity retrieval-based post-editing system that corrects factual errors in abstractive summaries by leveraging evidence sentences, achieving high success rate, interpretability, and faster processing.

Contribution

RFEC is a novel factual error correction method that uses entity retrieval and evidence sentences to improve accuracy and speed over existing autoregressive approaches.

Findings

RFEC outperforms baseline methods in factual error correction.

RFEC achieves faster correction speeds.

RFEC maintains high interpretability in the correction process.

Abstract

Despite the recent advancements in abstractive summarization systems leveraged from large-scale datasets and pre-trained language models, the factual correctness of the summary is still insufficient. One line of trials to mitigate this problem is to include a post-editing process that can detect and correct factual errors in the summary. In building such a post-editing system, it is strongly required that 1) the process has a high success rate and interpretability and 2) has a fast running time. Previous approaches focus on regeneration of the summary using the autoregressive models, which lack interpretability and require high computing resources. In this paper, we propose an efficient factual error correction system RFEC based on entities retrieval post-editing process. RFEC first retrieves the evidence sentences from the original document by comparing the sentences with the target summary. This approach greatly reduces the length of text for a system to analyze. Next, RFEC detects the entity-level errors in the summaries by considering the evidence sentences and substitutes the wrong entities with the accurate entities from the evidence sentences. Experimental results show that our proposed error correction system shows more competitive performance than baseline methods in correcting the factual errors with a much faster speed.