Factual Error Correction for Abstractive Summaries Using Entity Retrieval
By Hwanhee Lee, Cheoneum Park, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Juae Kim, Kyomin Jung. 2022
15 citations recorded by the source corpus.
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 system, it is strongly required that 1) the process has a high success rate and interpretability and 2) it has a fast running time. Previous approaches focus on the regeneration of the summary, resulting in low interpretability and high computing resources. In this paper, we propose an efficient factual error correction system RFEC based on entity retrieval. RFEC first retrieves the evidence sentences from the original document by comparing the sentences with the target summary to reduce the length of the text to analyze. Next, RFEC detects entity-level errors in the summaries using 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 factual errors with a much faster speed.
Subfields: Natural Language Processing, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Yulia Tsvetkov
- Vidhisha Balachandran
- Sachin Kumar
- William W. Cohen
- Antonios Anastasopoulos
- Hannaneh Hajishirzi
- Lucille Njoo
- Mohit Bansal
In Safety, Robustness & Interpretability
- Sachin Kumar
- Vidhisha Balachandran
- Lucille Njoo
- Antonios Anastasopoulos
- Yulia Tsvetkov
- Hannaneh Hajishirzi
- William W. Cohen
Citations in the corpus
- Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey (2022, background): “, 2020) and semi-supervised methods to correct factual errors (Cao et al., 2020; Lee et al., 2022a; Balachandran et al., 2022).”
- Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling (2022, methodology): “Lee et al. (2022b) use similar masked infilling to generate training data for such metrics.”