Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDoes local pruning offer task-specific models to learn effectively ?
هل توفر التقليمات المحلية نماذج خاصة بالمهام للتعلم بفعالية؟
82
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أدت الحاجة إلى نشر النماذج المدربة مسبقا على نطاق واسع على أجهزة الحافة بموجب موارد حسابية محدودة إلى بحث كبير لضغط هذه النماذج الكبيرة. ومع ذلك، تم إيلاء اهتمام أقل لضغط النماذج الخاصة المهام. في هذا العمل، نحقق في أساليب مختلفة من التقليم غير منظم في نماذج ذات المهام الخاصة بمهام تحليل المعنويات المستندة إلى جانب جانب الجسيم. على وجه التحديد، نقوم بتحليل الاختلافات في ديناميات التعلم من النماذج ذات التذرية باستخدام تقنيات التقليم القياسية لتحقيق شبكات متفرقة عالية الأداء. نقوم بتطوير فرضية لإظهار فعالية التشذيب المحلي على التقليم العالمي بالنظر إلى نموذج سي إن إن بسيط. في وقت لاحق، نحن نستخدم الفرضية لإظهار فعالية النموذج الحديثة المعادلة مقارنة بالنموذج المفرط من أحدث المعلمات تحت إعدادتين، أول النظر في الأساس لنفس المهمة المستخدمة ل توليد الفرضية، أي استخراج الآراء والثاني النظر في مهمة مختلفة، أي تحليل المعرفات. كما نقدم المناقشة المتعلقة بتعميم الفرضية التقليم.
The need to deploy large-scale pre-trained models on edge devices under limited computational resources has led to substantial research to compress these large models. However, less attention has been given to compress the task-specific models. In this work, we investigate the different methods of unstructured pruning on task-specific models for Aspect-based Sentiment Analysis (ABSA) tasks. Specifically, we analyze differences in the learning dynamics of pruned models by using the standard pruning techniques to achieve high-performing sparse networks. We develop a hypothesis to demonstrate the effectiveness of local pruning over global pruning considering a simple CNN model. Later, we utilize the hypothesis to demonstrate the efficacy of the pruned state-of-the-art model compared to the over-parameterized state-of-the-art model under two settings, the first considering the baselines for the same task used for generating the hypothesis, i.e., aspect extraction and the second considering a different task, i.e., sentiment analysis. We also provide discussion related to the generalization of the pruning hypothesis.
References used
https://aclanthology.org/
rate research
Read More
In this work, we design an end-to-end model for poetry generation based on conditioned recurrent neural network (RNN) language models whose goal is to learn stylistic features (poem length, sentiment, alliteration, and rhyming) from examples alone. W
e show this model successfully learns the meaning' of length and sentiment, as we can control it to generate longer or shorter as well as more positive or more negative poems. However, the model does not grasp sound phenomena like alliteration and rhyming, but instead exploits low-level statistical cues. Possible reasons include the size of the training data, the relatively low frequency and difficulty of these sublexical phenomena as well as model biases. We show that more recent GPT-2 models also have problems learning sublexical phenomena such as rhyming from examples alone.
People convey their intention and attitude through linguistic styles of the text that they write. In this study, we investigate lexicon usages across styles throughout two lenses: human perception and machine word importance, since words differ in th
e strength of the stylistic cues that they provide. To collect labels of human perception, we curate a new dataset, Hummingbird, on top of benchmarking style datasets. We have crowd workers highlight the representative words in the text that makes them think the text has the following styles: politeness, sentiment, offensiveness, and five emotion types. We then compare these human word labels with word importance derived from a popular fine-tuned style classifier like BERT. Our results show that the BERT often finds content words not relevant to the target style as important words used in style prediction, but humans do not perceive the same way even though for some styles (e.g., positive sentiment and joy) human- and machine-identified words share significant overlap for some styles.
Large pretrained language models using the transformer neural network architecture are becoming a dominant methodology for many natural language processing tasks, such as question answering, text classification, word sense disambiguation, text comple
tion and machine translation. Commonly comprising hundreds of millions of parameters, these models offer state-of-the-art performance, but at the expense of interpretability. The attention mechanism is the main component of transformer networks. We present AttViz, a method for exploration of self-attention in transformer networks, which can help in explanation and debugging of the trained models by showing associations between text tokens in an input sequence. We show that existing deep learning pipelines can be explored with AttViz, which offers novel visualizations of the attention heads and their aggregations. We implemented the proposed methods in an online toolkit and an offline library. Using examples from news analysis, we demonstrate how AttViz can be used to inspect and potentially better understand what a model has learned.
After a neural sequence model encounters an unexpected token, can its behavior be predicted? We show that RNN and transformer language models exhibit structured, consistent generalization in out-of-distribution contexts. We begin by introducing two i
dealized models of generalization in next-word prediction: a lexical context model in which generalization is consistent with the last word observed, and a syntactic context model in which generalization is consistent with the global structure of the input. In experiments in English, Finnish, Mandarin, and random regular languages, we demonstrate that neural language models interpolate between these two forms of generalization: their predictions are well-approximated by a log-linear combination of lexical and syntactic predictive distributions. We then show that, in some languages, noise mediates the two forms of generalization: noise applied to input tokens encourages syntactic generalization, while noise in history representations encourages lexical generalization. Finally, we offer a preliminary theoretical explanation of these results by proving that the observed interpolation behavior is expected in log-linear models with a particular feature correlation structure. These results help explain the effectiveness of two popular regularization schemes and show that aspects of sequence model generalization can be understood and controlled.
Transformers-based pretrained language models achieve outstanding results in many well-known NLU benchmarks. However, while pretraining methods are very convenient, they are expensive in terms of time and resources. This calls for a study of the impa
ct of pretraining data size on the knowledge of the models. We explore this impact on the syntactic capabilities of RoBERTa, using models trained on incremental sizes of raw text data. First, we use syntactic structural probes to determine whether models pretrained on more data encode a higher amount of syntactic information. Second, we perform a targeted syntactic evaluation to analyze the impact of pretraining data size on the syntactic generalization performance of the models. Third, we compare the performance of the different models on three downstream applications: part-of-speech tagging, dependency parsing and paraphrase identification. We complement our study with an analysis of the cost-benefit trade-off of training such models. Our experiments show that while models pretrained on more data encode more syntactic knowledge and perform better on downstream applications, they do not always offer a better performance across the different syntactic phenomena and come at a higher financial and environmental cost.
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
