Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userControlled Neural Sentence-Level Reframing of News Articles
تسيطر الجملة العصبية على مستوى إعادة تصنيع المواد الأخبار
364
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن تأطير مقالة إخبارية تعني تصوير الحدث المبلغ عنها من منظور محدد، على سبيل المثال، من منظور اقتصادي أو صحي. Reframing وسائل لتغيير هذا المنظور. اعتمادا على الجمهور أو الحضور، يمكن أن تصادف REFRIMING ضرورية لتحقيق التأثير المرغوب على القراء. يرتبط Reframing بتكييف الأسلوب والشاعر، والتي يمكن معالجة تقنيات توليد النص العصبي. ومع ذلك، فإن الأمر أكثر تحديا لأن تغيير الإطار يتطلب إعادة كتابة الجمل بأكملها بدلا من عبارات واحدة. في هذه الورقة، ندرس كيفية إعادة صياغة الجمل في مقالات إخبارية مع الحفاظ على تماسكها إلى السياق. نتعامل مع REMREMING كمركز ملء على مستوى الجملة الذي نربط النماذج العصبية على كوربوس موجود للإطار الوسائط. لتوجيه التدريب، نقترح ثلاث استراتيجيات: محاكمة اللغة المؤطرة، والحفاظ على الكيانات المسماة، والتعلم الخصم. نقوم بتقييم النماذج المعنية تلقائيا وتدويا من أجل اتساق الموضوع والتماسك والتعداد الناجح. تشير نتائجنا إلى أن إنشاء نص مؤطر بشكل صحيح يعمل بشكل جيد ولكن مع المفاضلات.
Framing a news article means to portray the reported event from a specific perspective, e.g., from an economic or a health perspective. Reframing means to change this perspective. Depending on the audience or the submessage, reframing can become necessary to achieve the desired effect on the readers. Reframing is related to adapting style and sentiment, which can be tackled with neural text generation techniques. However, it is more challenging since changing a frame requires rewriting entire sentences rather than single phrases. In this paper, we study how to computationally reframe sentences in news articles while maintaining their coherence to the context. We treat reframing as a sentence-level fill-in-the-blank task for which we train neural models on an existing media frame corpus. To guide the training, we propose three strategies: framed-language pretraining, named-entity preservation, and adversarial learning. We evaluate respective models automatically and manually for topic consistency, coherence, and successful reframing. Our results indicate that generating properly-framed text works well but with tradeoffs.
References used
https://aclanthology.org/
rate research
Read More
We rely on arguments in our daily lives to deliver our opinions and base them on evidence, making them more convincing in turn. However, finding and formulating arguments can be challenging. In this work, we present the Arg-CTRL - a language model fo
r argument generation that can be controlled to generate sentence-level arguments for a given topic, stance, and aspect. We define argument aspect detection as a necessary method to allow this fine-granular control and crowdsource a dataset with 5,032 arguments annotated with aspects. Our evaluation shows that the Arg-CTRL is able to generate high-quality, aspect-specific arguments, applicable to automatic counter-argument generation. We publish the model weights and all datasets and code to train the Arg-CTRL.
Arabic sentiment analysis research existing currently is very limited. While sentiment analysis has many applications in English, the Arabic language is still recognizing its early steps in this field. In this paper, we show an application
on Arabic
sentiment analysis by implementing a sentiment classification for Arabic tweets. The retrieved tweets are analyzed to provide their sentiments polarity (positive, or negative). Since, this data is collected from the social network Twitter; it has its importance for the Middle East region, which mostly speaks Arabic
Automatic news recommendation has gained much attention from the academic community and industry. Recent studies reveal that the key to this task lies within the effective representation learning of both news and users. Existing works typically encod
e news title and content separately while neglecting their semantic interaction, which is inadequate for news text comprehension. Besides, previous models encode user browsing history without leveraging the structural correlation of user browsed news to reflect user interests explicitly. In this work, we propose a news recommendation framework consisting of collaborative news encoding (CNE) and structural user encoding (SUE) to enhance news and user representation learning. CNE equipped with bidirectional LSTMs encodes news title and content collaboratively with cross-selection and cross-attention modules to learn semantic-interactive news representations. SUE utilizes graph convolutional networks to extract cluster-structural features of user history, followed by intra-cluster and inter-cluster attention modules to learn hierarchical user interest representations. Experiment results on the MIND dataset validate the effectiveness of our model to improve the performance of news recommendation.
Morphological tasks have gained decent popularity within the NLP community in the recent years, with large multi-lingual datasets providing morphological analysis of words, either in or out of context. However, the lack of a clear linguistic definiti
on for words destines the annotative work to be incomplete and mired in inconsistencies, especially cross-linguistically. In this work we expand morphological inflection of words to inflection of sentences to provide true universality disconnected from orthographic traditions of white-space usage. To allow annotation for sentence-inflection we define a morphological annotation scheme by a fixed set of inflectional features. We present a small cross-linguistic dataset including semi-manually generated simple sentences in 4 typologically diverse languages annotated according to our suggested scheme, and show that the task of reinflection gets substantially more difficult but that the change of scope from words to well-defined sentences allows interface with contextualized language models.
Document-level event extraction is critical to various natural language processing tasks for providing structured information. Existing approaches by sequential modeling neglect the complex logic structures for long texts. In this paper, we leverage
the entity interactions and sentence interactions within long documents and transform each document into an undirected unweighted graph by exploiting the relationship between sentences. We introduce the Sentence Community to represent each event as a subgraph. Furthermore, our framework SCDEE maintains the ability to extract multiple events by sentence community detection using graph attention networks and alleviate the role overlapping issue by predicting arguments in terms of roles. Experiments demonstrate that our framework achieves competitive results over state-of-the-art methods on the large-scale document-level event extraction dataset.
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
