تظهر هذه الورقة أن عصير التفاح، مقياس التقييم التقليدي لوصف الصورة، لا يعمل بشكل صحيح على مجموعات البيانات حيث يكون عدد الكلمات في الجملة أكبر بكثير من تلك الموجودة في مجموعة بيانات التسميات التوضيحية MS COCO.نظهر أيضا أن CIDER-D لديه أداء يعوقه عدم وجود جمل مرجعية متعددة والتباين العالي لطول الجملة.لتجاوز هذه المشكلة، نقدم Cider-R، الذي يحسن CIDER-D، مما يجعله أكثر مرونة في التعامل مع مجموعات البيانات ذات تباين طول الجملة.نوضح أن عصير التفاح هو أكثر دقة وأقرب من الحكم الإنساني من عصير التفاح.Cider-R هو أكثر قوة فيما يتعلق بعدد المراجع المتاحة.تكشف نتائجنا أن استخدام تدريب التسلسل الحرج الذاتي لتحسين عصير التفاح - يولد تعليقا وصفيا.في المقابل، عند تحسين CIDER-D، يميل طول التسميات التوضيحية التي تم إنشاؤها إلى أن تكون مشابهة للطول المرجعي.ومع ذلك، تكرر النماذج أيضا عدة مرات نفس الكلمة لزيادة طول الجملة.
This paper shows that CIDEr-D, a traditional evaluation metric for image description, does not work properly on datasets where the number of words in the sentence is significantly greater than those in the MS COCO Captions dataset. We also show that CIDEr-D has performance hampered by the lack of multiple reference sentences and high variance of sentence length. To bypass this problem, we introduce CIDEr-R, which improves CIDEr-D, making it more flexible in dealing with datasets with high sentence length variance. We demonstrate that CIDEr-R is more accurate and closer to human judgment than CIDEr-D; CIDEr-R is more robust regarding the number of available references. Our results reveal that using Self-Critical Sequence Training to optimize CIDEr-R generates descriptive captions. In contrast, when CIDEr-D is optimized, the generated captions' length tends to be similar to the reference length. However, the models also repeat several times the same word to increase the sentence length.
References used
https://aclanthology.org/
We present a systematic procedure for interrater disagreement resolution. The procedure is general, but of particular use in multiple-annotator tasks geared towards ground truth construction. We motivate our proposal by arguing that, barring cases in
In this scientific paper we dealt with three different types of
homomorphisms between two given ideals in a ring with unity shown as
follows: ring homomorphism, R- module homomorphism and ideal
homomorphism, which were supported by several example
Pre-trained language models (PTLMs) have achieved impressive performance on commonsense inference benchmarks, but their ability to employ commonsense to make robust inferences, which is crucial for effective communications with humans, is debated. In
This paper discusses a classification-based approach to machine translation evaluation, as opposed to a common regression-based approach in the WMT Metrics task. Recent machine translation usually works well but sometimes makes critical errors due to
In this paper we present a deep learning code completion model for the R language. We introduce several techniques to utilize language modeling based architecture in the code completion task. With these techniques, the model requires low resources, b