Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCIDEr-R: Robust Consensus-based Image Description Evaluation
Cider-R: تقييم الدلالة القائمة على توافق الآراء
324
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
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/
rate research
Read More
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
which the researchers' goal is to elicit different viewpoints, interrater disagreement is a sign of poor quality in the design or the description of a task. Consensus among annotators, we maintain, should be striven for, through a systematic procedure for disagreement resolution such as the one we describe.
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
s.
Furthermore, we prove that the family of ideals in a ring R with ring, R -
module and ideal homomorphisms forms the category of ideals of the first,
second and third type, respectively. The next step was dedicated to support all
previous ideals by examples and functor between such categories.
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
the pursuit of advancing fluid human-AI communication, we propose a new challenge, RICA: Robust Inference using Commonsense Axioms, that evaluates robust commonsense inference despite textual perturbations. To generate data for this challenge, we develop a systematic and scalable procedure using commonsense knowledge bases and probe PTLMs across two different evaluation settings. Extensive experiments on our generated probe sets with more than 10k statements show that PTLMs perform no better than random guessing on the zero-shot setting, are heavily impacted by statistical biases, and are not robust to perturbation attacks. We also find that fine-tuning on similar statements offer limited gains, as PTLMs still fail to generalize to unseen inferences. Our new large-scale benchmark exposes a significant gap between PTLMs and human-level language understanding and offers a new challenge for PTLMs to demonstrate commonsense.
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
just a few wrong word choices. Our classification-based approach focuses on such errors using several error type labels, for practical machine translation evaluation in an age of neural machine translation. We made additional annotations on the WMT 2015-2017 Metrics datasets with fluency and adequacy labels to distinguish different types of translation errors from syntactic and semantic viewpoints. We present our human evaluation criteria for the corpus development and automatic evaluation experiments using the corpus. The human evaluation corpus will be publicly available upon publication.
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
ut still achieves high quality. We also present an evaluation dataset for the R language completion task. Our dataset contains multiple autocompletion usage contexts that provides robust validation results. The dataset is publicly available.
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
