中文
相关论文

相关论文: Towards Question-Answering as an Automatic Metric …

200 篇论文

Factual consistency is an essential quality of text summarization models in practical settings. Existing work in evaluating this dimension can be broadly categorized into two lines of research, entailment-based and question answering…

计算与语言 · 计算机科学 2022-05-02 Alexander R. Fabbri , Chien-Sheng Wu , Wenhao Liu , Caiming Xiong

Reference-based metrics such as ROUGE or BERTScore evaluate the content quality of a summary by comparing the summary to a reference. Ideally, this comparison should measure the summary's information quality by calculating how much…

计算与语言 · 计算机科学 2020-10-26 Daniel Deutsch , Dan Roth

Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and produce aggregate scores without explaining deficiencies or guiding improvement,…

计算与语言 · 计算机科学 2026-04-29 Huyen Nguyen , Haoxuan Zhang , Yang Zhang , Haihua Chen , Junhua Ding

Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments. To alleviate this issue, recent work has proposed evaluation metrics which rely…

Video-to-text summarization remains underexplored in terms of comprehensive evaluation methods. Traditional n-gram overlap-based metrics and recent large language model (LLM)-based approaches depend heavily on human-written reference…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Woojun Jung , Junyeong Kim

The task of automatic text summarization has gained a lot of traction due to the recent advancements in machine learning techniques. However, evaluating the quality of a generated summary remains to be an open problem. The literature has…

计算与语言 · 计算机科学 2022-01-25 Raghav Jain , Vaibhav Mavi , Anubhav Jangra , Sriparna Saha

Neural abstractive summarization models are prone to generate content inconsistent with the source document, i.e. unfaithful. Existing automatic metrics do not capture such mistakes effectively. We tackle the problem of evaluating…

计算与语言 · 计算机科学 2020-10-13 Esin Durmus , He He , Mona Diab

The development of methods to deal with the informative contents of the text units in the matching process is a major challenge in automatic summary evaluation systems that use fixed n-gram matching. The limitation causes inaccurate…

计算与语言 · 计算机科学 2015-05-26 Fatma Elghannam , Tarek El-Shishtawy

State-of-the-art summarization systems can generate highly fluent summaries. These summaries, however, may contain factual inconsistencies and/or information not present in the source. Hence, an important component of assessing the quality…

计算与语言 · 计算机科学 2023-09-11 Potsawee Manakul , Adian Liusie , Mark J. F. Gales

Recent work in the field of automatic summarization and headline generation focuses on maximizing ROUGE scores for various news datasets. We present an alternative, extrinsic, evaluation metric for this task, Answering Performance for…

计算与语言 · 计算机科学 2019-06-04 Matan Eyal , Tal Baumel , Michael Elhadad

Aspect-based summarization aims to generate summaries that highlight specific aspects of a text, enabling more personalized and targeted summaries. However, its application to books remains unexplored due to the difficulty of constructing…

计算与语言 · 计算机科学 2025-11-11 Ryuhei Miyazato , Ting-Ruen Wei , Xuyang Wu , Hsin-Tai Wu , Kei Harada

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain. Recently, there have been a…

计算与语言 · 计算机科学 2022-05-06 Forrest Sheng Bao , Hebi Li , Ge Luo , Minghui Qiu , Yinfei Yang , Youbiao He , Cen Chen

Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder based similarity…

计算与语言 · 计算机科学 2023-09-22 Matteo Gabburo , Siddhant Garg , Rik Koncel Kedziorski , Alessandro Moschitti

The quality of a summarization evaluation metric is quantified by calculating the correlation between its scores and human annotations across a large number of summaries. Currently, it is unclear how precise these correlation estimates are,…

计算与语言 · 计算机科学 2021-07-28 Daniel Deutsch , Rotem Dror , Dan Roth

How to properly conduct human evaluations for text summarization is a longstanding challenge. The Pyramid human evaluation protocol, which assesses content selection by breaking the reference summary into subunits and verifying their…

计算与语言 · 计算机科学 2025-10-08 Shiyue Zhang , David Wan , Arie Cattan , Ayal Klein , Ido Dagan , Mohit Bansal

Practical applications of abstractive summarization models are limited by frequent factual inconsistencies with respect to their input. Existing automatic evaluation metrics for summarization are largely insensitive to such errors. We…

计算与语言 · 计算机科学 2020-04-10 Alex Wang , Kyunghyun Cho , Mike Lewis

Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a…

计算与语言 · 计算机科学 2018-04-12 Ping Chen , Fei Wu , Tong Wang , Wei Ding

ROUGE is a widely adopted, automatic evaluation measure for text summarization. While it has been shown to correlate well with human judgements, it is biased towards surface lexical similarities. This makes it unsuitable for the evaluation…

计算与语言 · 计算机科学 2015-08-26 Jun-Ping Ng , Viktoria Abrecht

Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non-differentiable, metrics that globally assess…

计算与语言 · 计算机科学 2019-09-05 Thomas Scialom , Sylvain Lamprier , Benjamin Piwowarski , Jacopo Staiano

Multimodal Large Language Models (MLLMs) have facilitated Multimodal Summarization with Multimodal Output (MSMO), wherein systems generate concise textual summaries accompanied by salient visuals from multimodal sources. However, current…

人工智能 · 计算机科学 2026-05-13 Abid Ali , Diego Molla-Aliod , Usman Naseem
‹ 上一页 1 2 3 10 下一页 ›