Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userConstructing contrastive samples via summarization for text classification with limited annotations
بناء عينات صغيرة من خلال تلخيص لتصنيف النص مع التعليقات التوضيحية المحدودة
289
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لقد ظهر التعلم الناقض كطريقة لتعلم التمثيل القوي ويسهل العديد من المهام المصب المختلفة خاصة عندما تكون البيانات الخاضعة للإشراف محدودة. كيفية بناء عينات مضاءة فعالة من خلال تكبير البيانات هي مفتاح نجاحها. على عكس مهام الرؤية، لم يتم التحقيق في طريقة تكبير البيانات للتعلم المتعاقل بما فيه الكفاية في مهام اللغة. في هذه الورقة، نقترح نهج رواية لبناء عينات صغيرة لمهام اللغة باستخدام تلخيص النص. نحن نستخدم هذه العينات للتعلم المتعاقل الخاضع للإشراف للحصول على تمثيلات نصية أفضل التي تنفصل إلى حد كبير مهام تصنيف النص بشراحي محدود. لمزيد من تحسين الطريقة، نخلط عينات من فئات مختلفة وإضافة تنظيم إضافي، يدعى Mixsum، بالإضافة إلى فقدان الانتروبيا. توضح التجارب في مجموعات بيانات تصنيف النص العالمي الحقيقي (Amazon-5، YELP-5، AG News، IMDB) فعالية إطار التعلم المقاوم للضبط المقترح مع تكبير البيانات القائمة على التلخصات وانتظام Mixsum.
Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is key to its success. Unlike vision tasks, the data augmentation method for contrastive learning has not been investigated sufficiently in language tasks. In this paper, we propose a novel approach to construct contrastive samples for language tasks using text summarization. We use these samples for supervised contrastive learning to gain better text representations which greatly benefit text classification tasks with limited annotations. To further improve the method, we mix up samples from different classes and add an extra regularization, named Mixsum, in addition to the cross-entropy-loss. Experiments on real-world text classification datasets (Amazon-5, Yelp-5, AG News, and IMDb) demonstrate the effectiveness of the proposed contrastive learning framework with summarization-based data augmentation and Mixsum regularization.
References used
https://aclanthology.org/
rate research
Read More
In this paper, we present coreference resolution experiments with a newly created multilingual corpus CorefUD (Nedoluzhko et al.,2021). We focus on the following languages: Czech, Russian, Polish, German, Spanish, and Catalan. In addition to monoling
ual experiments, we combine the training data in multilingual experiments and train two joined models - for Slavic languages and for all the languages together. We rely on an end-to-end deep learning model that we slightly adapted for the CorefUD corpus. Our results show that we can profit from harmonized annotations, and using joined models helps significantly for the languages with smaller training data.
Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers. Despite being successful, the word sequences produced in s
uch attacks are often ungrammatical and can be easily distinguished from natural text. We develop adversarial attacks that appear closer to natural English phrases and yet confuse classification systems when added to benign inputs. We leverage an adversarially regularized autoencoder (ARAE) to generate triggers and propose a gradient-based search that aims to maximize the downstream classifier's prediction loss. Our attacks effectively reduce model accuracy on classification tasks while being less identifiable than prior models as per automatic detection metrics and human-subject studies. Our aim is to demonstrate that adversarial attacks can be made harder to detect than previously thought and to enable the development of appropriate defenses.
Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much emphasis o
n how to well generalize models to new tasks. In this work, we propose an information disentanglement based regularization method for continual learning on text classification. Our proposed method first disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task, and further regularizes these representations differently to better constrain the knowledge required to generalize. We also introduce two simple auxiliary tasks: next sentence prediction and task-id prediction, for learning better generic and specific representation spaces. Experiments conducted on large-scale benchmarks demonstrate the effectiveness of our method in continual text classification tasks with various sequences and lengths over state-of-the-art baselines. We have publicly released our code at https://github.com/GT-SALT/IDBR.
Difficult samples of the minority class in imbalanced text classification are usually hard to be classified as they are embedded into an overlapping semantic region with the majority class. In this paper, we propose a Mutual Information constrained S
emantically Oversampling framework (MISO) that can generate anchor instances to help the backbone network determine the re-embedding position of a non-overlapping representation for each difficult sample. MISO consists of (1) a semantic fusion module that learns entangled semantics among difficult and majority samples with an adaptive multi-head attention mechanism, (2) a mutual information loss that forces our model to learn new representations of entangled semantics in the non-overlapping region of the minority class, and (3) a coupled adversarial encoder-decoder that fine-tunes disentangled semantic representations to remain their correlations with the minority class, and then using these disentangled semantic representations to generate anchor instances for each difficult sample. Experiments on a variety of imbalanced text classification tasks demonstrate that anchor instances help classifiers achieve significant improvements over strong baselines.
Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging
, primarily due to the lack of a gold standard data set and high context dependencies. This paper presents BABE, a robust and diverse data set created by trained experts, for media bias research. We also analyze why expert labeling is essential within this domain. Our data set offers better annotation quality and higher inter-annotator agreement than existing work. It consists of 3,700 sentences balanced among topics and outlets, containing media bias labels on the word and sentence level. Based on our data, we also introduce a way to detect bias-inducing sentences in news articles automatically. Our best performing BERT-based model is pre-trained on a larger corpus consisting of distant labels. Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0.804, outperforming existing methods.
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
