Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userVisual News: Benchmark and Challenges in News Image Captioning
أخبار البصرية: المعيار والتحديات في أخبار الصورة التسمية
329
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقترح أن نقترح Captioner أخبار البصرية، وهو نموذج كيائن كيائن لمهمة تقسيم صورة الأخبار. نقدم أيضا Visual News، وهو معيار واسع النطاق يتكون من أكثر من مليون صورة إخبارية إلى جانب المقالات الإخبارية المرتبطة، وتستياؤ الصور، ومعلومات المؤلف، والبيانات الوصفية الأخرى. على عكس مهمة تقسيم الصور القياسية، تصور الصور الأخبار المواقف التي يكون فيها الأشخاص والمواقع والأحداث ذات أهمية قصوى. يمكن أن تجمع طريقةنا المقترحة بشكل فعال بين الميزات المرئية والنصية لتوليد التسميات التوضيحية مع معلومات أكثر ثراء مثل الأحداث والكيانات. وبشكل أكثر تحديدا، تم تصميمها على بنية المحولات، يتم تزويد نموذجنا بمزيد من المجهز بتقنيات الانصهار متعددة الوسائط على الرواية وآليات الاهتمام، والتي تم تصميمها لتوليد كيانات اسمه أكثر دقة. تستخدم طريقتنا معلمات أقل بكثير مع تحقيق نتائج تنبؤ أفضل قليلا من الأساليب المنافسة. توضح مجموعة بيانات الأخبار المرئية الأكبر والأكثر تنوعا التحديات المتبقية في تصوير الصور الإخبارية.
We propose Visual News Captioner, an entity-aware model for the task of news image captioning. We also introduce Visual News, a large-scale benchmark consisting of more than one million news images along with associated news articles, image captions, author information, and other metadata. Unlike the standard image captioning task, news images depict situations where people, locations, and events are of paramount importance. Our proposed method can effectively combine visual and textual features to generate captions with richer information such as events and entities. More specifically, built upon the Transformer architecture, our model is further equipped with novel multi-modal feature fusion techniques and attention mechanisms, which are designed to generate named entities more accurately. Our method utilizes much fewer parameters while achieving slightly better prediction results than competing methods. Our larger and more diverse Visual News dataset further highlights the remaining challenges in captioning news images.
References used
https://aclanthology.org/
rate research
Read More
The task of news article image captioning aims to generate descriptive and informative captions for news article images. Unlike conventional image captions that simply describe the content of the image in general terms, news image captions follow jou
rnalistic guidelines and rely heavily on named entities to describe the image content, often drawing context from the whole article they are associated with. In this work, we propose a new approach to this task, motivated by caption guidelines that journalists follow. Our approach, Journalistic Guidelines Aware News Image Captioning (JoGANIC), leverages the structure of captions to improve the generation quality and guide our representation design. Experimental results, including detailed ablation studies, on two large-scale publicly available datasets show that JoGANIC substantially outperforms state-of-the-art methods both on caption generation and named entity related metrics.
The last several years have seen a massive increase in the quantity and influence of disinformation being spread online. Various approaches have been developed to target the process at different stages from identifying sources to tracking distributio
n in social media to providing follow up debunks to people who have encountered the disinformation. One common conclusion in each of these approaches is that disinformation is too nuanced and subjective a topic for fully automated solutions to work but the quantity of data to process and cross-reference is too high for humans to handle unassisted. Ultimately, the problem calls for a hybrid approach of human experts with technological assistance. In this paper we will demonstrate the application of certain state-of-the-art NLP techniques in assisting expert debunkers and fact checkers as well as the role of these NLP algorithms within a more holistic approach to analyzing and countering the spread of disinformation. We will present a multilingual corpus of disinformation and debunks which contains text, concept tags, images and videos as well as various methods for searching and leveraging the content.
We propose MultiOpEd, an open-domain news editorial corpus that supports various tasks pertaining to the argumentation structure in news editorials, focusing on automatic perspective discovery. News editorial is a genre of persuasive text, where the
argumentation structure is usually implicit. However, the arguments presented in an editorial typically center around a concise, focused thesis, which we refer to as their perspective. MultiOpEd aims at supporting the study of multiple tasks relevant to automatic perspective discovery, where a system is expected to produce a single-sentence thesis statement summarizing the arguments presented. We argue that identifying and abstracting such natural language perspectives from editorials is a crucial step toward studying the implicit argumentation structure in news editorials. We first discuss the challenges and define a few conceptual tasks towards our goal. To demonstrate the utility of MultiOpEd and the induced tasks, we study the problem of perspective summarization in a multi-task learning setting, as a case study. We show that, with the induced tasks as auxiliary tasks, we can improve the quality of the perspective summary generated. We hope that MultiOpEd will be a useful resource for future studies on argumentation in the news editorial domain.
We present an actor-critic framework to induce subtopical structures in a news article for news discourse profiling. The model uses multiple critics that act according to known subtopic structures while the actor aims to outperform them. The content
structures constitute sentences that represent latent subtopic boundaries. Then, we introduce a hierarchical neural network that uses the identified subtopic boundary sentences to model multi-level interaction between sentences, subtopics, and the document. Experimental results and analyses on the NewsDiscourse corpus show that the actor model learns to effectively segment a document into subtopics and improves the performance of the hierarchical model on the news discourse profiling task.
While COVID-19 vaccines are finally becoming widely available, a second pandemic that revolves around the circulation of anti-vaxxer fake news'' may hinder efforts to recover from the first one. With this in mind, we performed an extensive analysis o
f Arabic and English tweets about COVID-19 vaccines, with focus on messages originating from Qatar. We found that Arabic tweets contain a lot of false information and rumors, while English tweets are mostly factual. However, English tweets are much more propagandistic than Arabic ones. In terms of propaganda techniques, about half of the Arabic tweets express doubt, and 1/5 use loaded language, while English tweets are abundant in loaded language, exaggeration, fear, name-calling, doubt, and flag-waving. Finally, in terms of framing, Arabic tweets adopt a health and safety perspective, while in English economic concerns dominate.
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
