Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSummEval: Re-evaluating Summarization Evaluation
Summeval: إعادة تقييم تقييم التلخيص
300
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
خلاص ندرة الدراسات الشاملة الحديثة بشأن مقاييس التقييم لتلخيص النص ونقص توافق الآراء بشأن بروتوكولات التقييم لا تزال تمنع التقدم المحرز. نحن نتطلع إلى أوجه القصور الموجودة لأساليب تقييم التلخيص على طول خمسة أبعاد: 1) نعيد تقييم 14 مقيط تقييم تلقائي في أزياء شاملة ومتسقة باستخدام مخرجات نموذج تلخيص العصبي جنبا إلى جنب مع التوضيحات البشرية الخبراء والجمهور؛ 2) نحن معيارون باستمرار 23 نماذج تلخيص حديثة باستخدام مقاييس التقييم التلقائي المذكورة أعلاه؛ 3) نحن نكذب أكبر مجموعة من الملخصات الناتجة عن النماذج المدربة على مجموعة بيانات CNN / DailyMail الأخبار ومشاركتها في شكل موحد؛ 4) نحن نفرا ومشاركة مجموعة أدوات توفر واجهة برمجة تطبيقية قابلة للتوسيع وغير موحدة لتقييم نماذج تلخيص عبر مجموعة واسعة من المقاييس التلقائية؛ 5) نحن نكذب ومشاركة أكبر وأكثرها تنوعا، من حيث الأنواع النموذجية، وجمع الأحكام البشرية من الملخصات التي تم إنشاؤها النموذجية على مجموعة بيانات CNN / Daily Mail المشروحة من قبل كلا من قضاة الخبراء والعاملين بمصدر الحشد. نأمل أن يساعد هذا العمل في تعزيز بروتوكول تقييم أكثر اكتمالا لتلخيص النص وكذلك البحث المسبق في تطوير مقاييس التقييم التي ترتبط بأحكام الإنسان بشكل أفضل.
Abstract The scarcity of comprehensive up-to-date studies on evaluation metrics for text summarization and the lack of consensus regarding evaluation protocols continue to inhibit progress. We address the existing shortcomings of summarization evaluation methods along five dimensions: 1) we re-evaluate 14 automatic evaluation metrics in a comprehensive and consistent fashion using neural summarization model outputs along with expert and crowd-sourced human annotations; 2) we consistently benchmark 23 recent summarization models using the aforementioned automatic evaluation metrics; 3) we assemble the largest collection of summaries generated by models trained on the CNN/DailyMail news dataset and share it in a unified format; 4) we implement and share a toolkit that provides an extensible and unified API for evaluating summarization models across a broad range of automatic metrics; and 5) we assemble and share the largest and most diverse, in terms of model types, collection of human judgments of model-generated summaries on the CNN/Daily Mail dataset annotated by both expert judges and crowd-source workers. We hope that this work will help promote a more complete evaluation protocol for text summarization as well as advance research in developing evaluation metrics that better correlate with human judgments.
References used
https://aclanthology.org/
rate research
Read More
Abstract 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,
nor whether differences between two metrics' correlations reflect a true difference or if it is due to mere chance. In this work, we address these two problems by proposing methods for calculating confidence intervals and running hypothesis tests for correlations using two resampling methods, bootstrapping and permutation. After evaluating which of the proposed methods is most appropriate for summarization through two simulation experiments, we analyze the results of applying these methods to several different automatic evaluation metrics across three sets of human annotations. We find that the confidence intervals are rather wide, demonstrating high uncertainty in the reliability of automatic metrics. Further, although many metrics fail to show statistical improvements over ROUGE, two recent works, QAEval and BERTScore, do so in some evaluation settings.1
Summarization systems are ultimately evaluated by human annotators and raters. Usually, annotators and raters do not reflect the demographics of end users, but are recruited through student populations or crowdsourcing platforms with skewed demograph
ics. For two different evaluation scenarios -- evaluation against gold summaries and system output ratings -- we show that summary evaluation is sensitive to protected attributes. This can severely bias system development and evaluation, leading us to build models that cater for some groups rather than others.
When developing topic models, a critical question that should be asked is: How well will this model work in an applied setting? Because standard performance evaluation of topic interpretability uses automated measures modeled on human evaluation test
s that are dissimilar to applied usage, these models' generalizability remains in question. In this paper, we probe the issue of validity in topic model evaluation and assess how informative coherence measures are for specialized collections used in an applied setting. Informed by the literature, we propose four understandings of interpretability. We evaluate these using a novel experimental framework reflective of varied applied settings, including human evaluations using open labeling, typical of applied research. These evaluations show that for some specialized collections, standard coherence measures may not inform the most appropriate topic model or the optimal number of topics, and current interpretability performance validation methods are challenged as a means to confirm model quality in the absence of ground truth data.
Although some recent works show potential complementarity among different state-of-the-art systems, few works try to investigate this problem in text summarization. Researchers in other areas commonly refer to the techniques of reranking or stacking
to approach this problem. In this work, we highlight several limitations of previous methods, which motivates us to present a new framework Refactor that provides a unified view of text summarization and summaries combination. Experimentally, we perform a comprehensive evaluation that involves twenty-two base systems, four datasets, and three different application scenarios. Besides new state-of-the-art results on CNN/DailyMail dataset (46.18 ROUGE-1), we also elaborate on how our proposed method addresses the limitations of the traditional methods and the effectiveness of the Refactor model sheds light on insight for performance improvement. Our system can be directly used by other researchers as an off-the-shelf tool to achieve further performance improvements. We open-source all the code and provide a convenient interface to use it: https://github.com/yixinL7/Refactoring-Summarization.
We present work on summarising deliberative processes for non-English languages. Unlike commonly studied datasets, such as news articles, this deliberation dataset reflects difficulties of combining multiple narratives, mostly of poor grammatical qua
lity, in a single text. We report an extensive evaluation of a wide range of abstractive summarisation models in combination with an off-the-shelf machine translation model. Texts are translated into English, summarised, and translated back to the original language. We obtain promising results regarding the fluency, consistency and relevance of the summaries produced. Our approach is easy to implement for many languages for production purposes by simply changing the translation model.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
