Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFinding Spoiler Bias in Tweets by Zero-shot Learning and Knowledge Distilling from Neural Text Simplification
العثور على التحيز المفسد في تغريدات التعلم الصفرية والمعارف من تبسيط النص العصبي
254
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الكشف التلقائي عن معلومات المؤامرة الحرجة في مراجعات عناصر الوسائط يشكل تحديات فريدة لكل من الحوسبة الاجتماعية واللغويات الحسابية. في هذه الورقة، نقترح إلقاء مشكلة اكتشاف تحيز المفسد في الخطاب عبر الإنترنت مهمة تبسيط النص. نحن تخمين أنه بالنسبة لزوج مستخدم العنصر، فإن مراجعة المستخدم الأكثر بساطة نتعلمه من ملخص عنصر أعلى احتمال تقديم المفسد. يشتمل نموذجنا العصبي على شبكة المحولات المتقدمة لتحتل شدة المفسد في تغريدات المستخدم. شيدنا مجموعة بيانات مستدامة مفلصة عالية الجودة كشط من تغريدات مراجعة غير مرغوبة وقترن بملخص العنوان وبيانات meta المستخرجة من مجال معين من الفيلم. إلى حد كبير، فإن نتائجنا الكمية والنوعية تزن في تأثير أداء وجود الكيان المسمى في ملخصات المؤامرة. أحصى ما يلاحظه على تقسيم وإعادة صياغة التراسل مع المعرفة المقطوعة من الإنجليزية في ويكيبيديا ومضربتها بشكل جيد في مجموعة بيانات الأفلام لدينا، فإن نموذجنا العصبي يظهر لتفوق كلا من خطوط طراز لغة وطيور أحادية الترجمة.
Automatic detection of critical plot information in reviews of media items poses unique challenges to both social computing and computational linguistics. In this paper we propose to cast the problem of discovering spoiler bias in online discourse as a text simplification task. We conjecture that for an item-user pair, the simpler the user review we learn from an item summary the higher its likelihood to present a spoiler. Our neural model incorporates the advanced transformer network to rank the severity of a spoiler in user tweets. We constructed a sustainable high-quality movie dataset scraped from unsolicited review tweets and paired with a title summary and meta-data extracted from a movie specific domain. To a large extent, our quantitative and qualitative results weigh in on the performance impact of named entity presence in plot summaries. Pretrained on a split-and-rephrase corpus with knowledge distilled from English Wikipedia and fine-tuned on our movie dataset, our neural model shows to outperform both a language modeler and monolingual translation baselines.
References used
https://aclanthology.org/
rate research
Read More
We propose a shared task on training instance selection for few-shot neural text generation. Large-scale pretrained language models have led to dramatic improvements in few-shot text generation. Nonetheless, almost all previous work simply applies ra
ndom sampling to select the few-shot training instances. Little to no attention has been paid to the selection strategies and how they would affect model performance. Studying the selection strategy can help us (1) make the most use of our annotation budget in downstream tasks and (2) better benchmark few-shot text generative models. We welcome submissions that present their selection strategies and the effects on the generation quality.
Emotion Classification is the task of automatically associating a text with a human emotion. State-of-the-art models are usually learned using annotated corpora or rely on hand-crafted affective lexicons. We present an emotion classification model th
at does not require a large annotated corpus to be competitive. We experiment with pretrained language models in both a zero-shot and few-shot configuration. We build several of such models and consider them as biased, noisy annotators, whose individual performance is poor. We aggregate the predictions of these models using a Bayesian method originally developed for modelling crowdsourced annotations. Next, we show that the resulting system performs better than the strongest individual model. Finally, we show that when trained on few labelled data, our systems outperform fully-supervised models.
Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of text and grap
h leveraging Reinforcement Learning to improve performance. Graph linearization enables us to re-frame both tasks as a sequence to sequence generation problem regardless of the generative direction, which in turn allows the use of Reinforcement Learning for sequence training where the model itself is employed as its own critic leading to Self-Critical Sequence Training (SCST). We present an extensive investigation demonstrating that the use of RL via SCST benefits graph and text generation on WebNLG+ 2020 and TekGen datasets. Our system provides state-of-the-art results on WebNLG+ 2020 by significantly improving upon published results from the WebNLG 2020+ Challenge for both text-to-graph and graph-to-text generation tasks. More details at https://github.com/IBM/regen.
Finding informative COVID-19 posts in a stream of tweets is very useful to monitor health-related updates. Prior work focused on a balanced data setup and on English, but informative tweets are rare, and English is only one of the many languages spok
en in the world. In this work, we introduce a new dataset of 5,000 tweets for finding informative COVID-19 tweets for Danish. In contrast to prior work, which balances the label distribution, we model the problem by keeping its natural distribution. We examine how well a simple probabilistic model and a convolutional neural network (CNN) perform on this task. We find a weighted CNN to work well but it is sensitive to embedding and hyperparameter choices. We hope the contributed dataset is a starting point for further work in this direction.
Text simplification is a valuable technique. However, current research is limited to sentence simplification. In this paper, we define and investigate a new task of document-level text simplification, which aims to simplify a document consisting of m
ultiple sentences. Based on Wikipedia dumps, we first construct a large-scale dataset named D-Wikipedia and perform analysis and human evaluation on it to show that the dataset is reliable. Then, we propose a new automatic evaluation metric called D-SARI that is more suitable for the document-level simplification task. Finally, we select several representative models as baseline models for this task and perform automatic evaluation and human evaluation. We analyze the results and point out the shortcomings of the baseline models.
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
