Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userKnodle: Modular Weakly Supervised Learning with PyTorch
Knodle: وحدات التعلم الخاضع للإشراف مع Pytorch
146
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تختلف استراتيجيات تحسين جودة التدريب والتنبؤ نماذج التعلم الآلي الأكثر إشرافا ضعيفا في مقدار ما يتم تصميمه إلى مهمة محددة أو متكاملة مع بنية نموذجية معينة. في هذا العمل، نقدم Knodle، وهو إطار برمجي يعامل شروح بيانات ضعيفة، ونماذج التعلم العميق، وطرق تحسين التدريب الخاضع للإشراف على أنه مكونات منفصلة وحديثة. يمنح هذا النزول عملية التدريب الوصول إلى المعلومات المحبوسة الدقيقة مثل خصائص مجموعة البيانات أو تطابقات القواعد المثيرة أو العناصر في نموذج التعلم العميق المستخدم في نهاية المطاف للتنبؤ. وبالتالي، يمكن لإطار عملنا أن يشمل مجموعة واسعة من أساليب التدريب لتحسين الإشراف الضعيف، بدءا من الأساليب التي تنظر فقط إلى ارتباطات القواعد وفئات الإخراج (بشكل مستقل عن نموذج تعلم الجهاز المدرب مع الملصقات الناتجة)، إلى تلك التي تسخير التفاعل من الشبكات العصبية والبيانات المسمى ضعيفة. نوضح الإمكانات القياسية للإطار مع مقارنة أداء العديد من التطبيقات المرجعية بشأن مجموعة مختارة من مجموعات البيانات المتوفرة بالفعل في ترنه.
Strategies for improving the training and prediction quality of weakly supervised machine learning models vary in how much they are tailored to a specific task or integrated with a specific model architecture. In this work, we introduce Knodle, a software framework that treats weak data annotations, deep learning models, and methods for improving weakly supervised training as separate, modular components. This modularization gives the training process access to fine-grained information such as data set characteristics, matches of heuristic rules, or elements of the deep learning model ultimately used for prediction. Hence, our framework can encompass a wide range of training methods for improving weak supervision, ranging from methods that only look at correlations of rules and output classes (independently of the machine learning model trained with the resulting labels), to those that harness the interplay of neural networks and weakly labeled data. We illustrate the benchmarking potential of the framework with a performance comparison of several reference implementations on a selection of datasets that are already available in Knodle.
References used
https://aclanthology.org/
rate research
Read More
Detecting out-of-domain (OOD) intents is crucial for the deployed task-oriented dialogue system. Previous unsupervised OOD detection methods only extract discriminative features of different in-domain intents while supervised counterparts can directl
y distinguish OOD and in-domain intents but require extensive labeled OOD data. To combine the benefits of both types, we propose a self-supervised contrastive learning framework to model discriminative semantic features of both in-domain intents and OOD intents from unlabeled data. Besides, we introduce an adversarial augmentation neural module to improve the efficiency and robustness of contrastive learning. Experiments on two public benchmark datasets show that our method can consistently outperform the baselines with a statistically significant margin.
Radiology report generation aims at generating descriptive text from radiology images automatically, which may present an opportunity to improve radiology reporting and interpretation. A typical setting consists of training encoder-decoder models on
image-report pairs with a cross entropy loss, which struggles to generate informative sentences for clinical diagnoses since normal findings dominate the datasets. To tackle this challenge and encourage more clinically-accurate text outputs, we propose a novel weakly supervised contrastive loss for medical report generation. Experimental results demonstrate that our method benefits from contrasting target reports with incorrect but semantically-close ones. It outperforms previous work on both clinical correctness and text generation metrics for two public benchmarks.
An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches i
mproved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgment.
Automatic summarization aims to extract important information from large amounts of textual data in order to create a shorter version of the original texts while preserving its information. Training traditional extractive summarization models relies
heavily on human-engineered labels such as sentence-level annotations of summary-worthiness. However, in many use cases, such human-engineered labels do not exist and manually annotating thousands of documents for the purpose of training models may not be feasible. On the other hand, indirect signals for summarization are often available, such as agent actions for customer service dialogues, headlines for news articles, diagnosis for Electronic Health Records, etc. In this paper, we develop a general framework that generates extractive summarization as a byproduct of supervised learning tasks for indirect signals via the help of attention mechanism. We test our models on customer service dialogues and experimental results demonstrated that our models can reliably select informative sentences and words for automatic summarization.
Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels,we are dedicated to the weakly superv
ised setting, where only video-level descriptions are provided for training. Most of the existing weakly supervised methods generate a candidate segment set and learn cross-modal alignment through a MIL-based framework. However, the temporal structure of the video as well as the complicated semantics in the sentence are lost during the learning. In this work, we propose a novel candidate-free framework: Fine-grained Semantic Alignment Network (FSAN), for weakly supervised TLG. Instead of view the sentence and candidate moments as a whole, FSAN learns token-by-clip cross-modal semantic alignment by an iterative cross-modal interaction module, generates a fine-grained cross-modal semantic alignment map, and performs grounding directly on top of the map. Extensive experiments are conducted on two widely-used benchmarks: ActivityNet-Captions, and DiDeMo, where our FSAN achieves state-of-the-art performance.
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
