paper-with-me

Papers

Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors

2022-05-25 · Liyan Tang, Tanya Goyal, Alexander R. Fabbri, Philippe Laban, Jiacheng Xu, Semih Yavuz, Wojciech Kryściński, Justin F. Rousseau, Greg Durrett

The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems' outputs. However, the ever-evolving nature of summarization systems, metrics, and annotated benchmarks makes factuality evaluation a moving target, and drawing clear comparisons among metrics has become increasingly difficult. In this work, we aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. We compare performance of state-of-the-art factuality metrics, including recent ChatGPT-based metrics, on this stratified benchmark and show that their performance varies significantly across different types of summarization models. Critically, our analysis shows that much of the recent improvement in the factuality detection space has been on summaries from older (pre-Transformer) models instead of more relevant recent summarization models. We further perform a finer-grained analysis per error-type and find similar performance variance across error types for different factuality metrics. Our results show that no one metric is superior in all settings or for all error types, and we provide recommendations for best practices given these insights.

📄 PDF Abstract BibTeX arXiv:2205.12854

Code (1)

liyan06/aggrefact 공식 구현

Tasks

Abstractive Text Summarization

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

What Have We Achieved on Text Summarization?

2020-10-09 · EMNLP 2020 11 · Dandan Huang, Leyang Cui, Sen yang, Guangsheng Bao 외

Deep learning has led to significant improvement in text summarization with various methods investigated and improved ROUGE scores reported over the years. However, gaps still exist between summaries produced by automati…

Text Summarization

This also affects the context - Errors in extraction based summaries

2012-05-01 · LREC 2012 5 · Thomas Kaspersson, Christian Smith, Henrik Danielsson, Arne J{\"o}nsson

Although previous studies have shown that errors occur in texts summarized by extraction based summarizers, no study has investigated how common different types of errors are and how that changes with degree of summariza…

Dimensionality Reduction

Evaluating the Factuality of Zero-shot Summarizers Across Varied Domains

2024-02-05 · Sanjana Ramprasad, Kundan Krishna, Zachary C Lipton, Byron C Wallace

Recent work has shown that large language models (LLMs) are capable of generating summaries zero-shot (i.e., without explicit supervision) that, under human assessment, are often comparable or even preferred to manually …

Articles

CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning

2021-12-16 · NAACL 2022 7 · Xiangru Tang, Arjun Nair, Borui Wang, Bingyao Wang 외

Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amo…

Abstractive Dialogue SummarizationMeeting SummarizationText Summarization

Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics

2021-04-27 · NAACL 2021 4 · Artidoro Pagnoni, Vidhisha Balachandran, Yulia Tsvetkov

Modern summarization models generate highly fluent but often factually unreliable outputs. This motivated a surge of metrics attempting to measure the factuality of automatically generated summaries. Due to the lack of c…

Abstractive Text Summarization