最近发布的GPT-3让我对NLP中的零学习和小样本的状态产生了兴趣。虽然大多数的零样本学习研究集中在计算机视觉,也有一些有趣的工作在NLP领域。

我将会写一系列的博文来涵盖现有的关于NLP零样本学习的研究。在这第一篇文章中,我将解释Pushp等人的论文“一次训练,到处测试:文本分类的零样本学习”。本文从2017年12月开始,首次提出了文本分类的零样本学习范式。

什么是零样本学习?

零样本学习是检测模型在训练中从未见过的类的能力。它类似于我们人类在没有明确监督的情况下归纳和识别新事物的能力。

例如,我们想要做情感分类和新闻分类。通常,我们将为每个数据集训练/微调一个新模型。相比之下,零样本学习,你可以直接执行任务,如情绪和新闻分类,没有任何特定的任务训练。

一次训练,随处测试

本文提出了一种简单的零样本分类方法。他们没有将文本分类为X类,而是将任务重新组织为二元分类,以确定文本和类是否相关。

https://amitness.com/2020/05/zero-shot-text-classification/

成为VIP会员查看完整内容
0
50

相关内容

题目:

Confidence-Aware Learning for Deep Neural Networks

简介:

尽管深度神经网络可以执行多种任务,但过分一致的预测问题限制了它们在许多安全关键型应用中的实际应用。已经提出了许多新的工作来减轻这个问题,但是大多数工作需要在训练和/或推理阶段增加计算成本,或者需要定制的体系结构来分别输出置信估计。在本文中,我们提出了一种使用新的损失函数训练深度神经网络的方法,称为正确排名损失,该方法将类别概率显式规范化,以便根据依据的有序等级更好地进行置信估计。所提出的方法易于实现,并且无需进行任何修改即可应用于现有体系结构。而且,它的训练计算成本几乎与传统的深度分类器相同,并且通过一次推断就可以输出可靠的预测。在分类基准数据集上的大量实验结果表明,所提出的方法有助于网络产生排列良好的置信度估计。我们还证明,它对于与置信估计,分布外检测和主动学习密切相关的任务十分有效。

成为VIP会员查看完整内容
0
33

本文综述了元学习在图像分类、自然语言处理和机器人技术等领域的应用。与深度学习不同,元学习使用较少的样本数据集,并考虑进一步改进模型泛化以获得更高的预测精度。我们将元学习模型归纳为三类: 黑箱适应模型、基于相似度的方法模型和元学习过程模型。最近的应用集中在将元学习与贝叶斯深度学习和强化学习相结合,以提供可行的集成问题解决方案。介绍了元学习方法的性能比较,并讨论了今后的研究方向。

成为VIP会员查看完整内容
0
158

元学习已被提出作为一个框架来解决具有挑战性的小样本学习设置。关键的思想是利用大量相似的小样本任务,以学习如何使基学习者适应只有少数标记的样本可用的新任务。由于深度神经网络(DNNs)倾向于只使用少数样本进行过度拟合,元学习通常使用浅层神经网络(SNNs),因此限制了其有效性。本文提出了一种新的学习方法——元转移学习(MTL)。具体来说,“meta”是指训练多个任务,“transfer”是通过学习每个任务的DNN权值的缩放和变换函数来实现的。此外,我们还介绍了作为一种有效的MTL学习课程的困难任务元批处理方案。我们使用(5类,1次)和(5类,5次)识别任务,在两个具有挑战性的小样本学习基准上进行实验:miniImageNet和Fewshot-CIFAR100。通过与相关文献的大量比较,验证了本文提出的HT元批处理方案训练的元转移学习方法具有良好的学习效果。消融研究还表明,这两种成分有助于快速收敛和高精度。

地址:

https://arxiv.org/abs/1812.02391

代码:

https://github.com/yaoyao-liu/meta-transfer-learning

成为VIP会员查看完整内容
0
100

Natural Language Processing (NLP) and especially natural language text analysis have seen great advances in recent times. Usage of deep learning in text processing has revolutionized the techniques for text processing and achieved remarkable results. Different deep learning architectures like CNN, LSTM, and very recent Transformer have been used to achieve state of the art results variety on NLP tasks. In this work, we survey a host of deep learning architectures for text classification tasks. The work is specifically concerned with the classification of Hindi text. The research in the classification of morphologically rich and low resource Hindi language written in Devanagari script has been limited due to the absence of large labeled corpus. In this work, we used translated versions of English data-sets to evaluate models based on CNN, LSTM and Attention. Multilingual pre-trained sentence embeddings based on BERT and LASER are also compared to evaluate their effectiveness for the Hindi language. The paper also serves as a tutorial for popular text classification techniques.

0
4
下载
预览

论文题目: Learning Conceptual-Contextual Embeddings for Medical Text

论文摘要:

对于自然语言理解任务来说,外部知识通常是有用的。本文介绍了一个上下文文本表示模型,称为概念上下文(CC)嵌入,它将结构化的知识合并到文本表示中。与实体嵌入方法不同,文中提到的方法将知识图编码到上下文模型中。就像预先训练好的语言模型一样,CC嵌入可以很容易地在广泛的任务中重用。模型利用语义泛化,有效地编码了庞大的UMLS数据库。电子实验健康记录(EHRs)和医疗文本处理基准表明,而使得模型大大提高了监督医疗NLP任务的性能。

成为VIP会员查看完整内容
0
38

In information retrieval (IR) and related tasks, term weighting approaches typically consider the frequency of the term in the document and in the collection in order to compute a score reflecting the importance of the term for the document. In tasks characterized by the presence of training data (such as text classification) it seems logical that the term weighting function should take into account the distribution (as estimated from training data) of the term across the classes of interest. Although `supervised term weighting' approaches that use this intuition have been described before, they have failed to show consistent improvements. In this article we analyse the possible reasons for this failure, and call consolidated assumptions into question. Following this criticism we propose a novel supervised term weighting approach that, instead of relying on any predefined formula, learns a term weighting function optimised on the training set of interest; we dub this approach \emph{Learning to Weight} (LTW). The experiments that we run on several well-known benchmarks, and using different learning methods, show that our method outperforms previous term weighting approaches in text classification.

0
8
下载
预览

Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP share the same learned (and static) set of filters for all input sentences. In this paper, we consider an approach of using a small meta network to learn context-sensitive convolutional filters for text processing. The role of meta network is to abstract the contextual information of a sentence or document into a set of input-aware filters. We further generalize this framework to model sentence pairs, where a bidirectional filter generation mechanism is introduced to encapsulate co-dependent sentence representations. In our benchmarks on four different tasks, including ontology classification, sentiment analysis, answer sentence selection, and paraphrase identification, our proposed model, a modified CNN with context-sensitive filters, consistently outperforms the standard CNN and attention-based CNN baselines. By visualizing the learned context-sensitive filters, we further validate and rationalize the effectiveness of proposed framework.

0
5
下载
预览
小贴士
相关论文
Ramchandra Joshi,Purvi Goel,Raviraj Joshi
4+阅读 · 2020年1月19日
Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
Jiawei Wu,Wenhan Xiong,William Yang Wang
16+阅读 · 2019年9月9日
Kamran Kowsari,Kiana Jafari Meimandi,Mojtaba Heidarysafa,Sanjana Mendu,Laura E. Barnes,Donald E. Brown
3+阅读 · 2019年4月25日
Few-shot Learning: A Survey
Yaqing Wang,Quanming Yao
294+阅读 · 2019年4月10日
Learning to Weight for Text Classification
Alejandro Moreo Fernández,Andrea Esuli,Fabrizio Sebastiani
8+阅读 · 2019年3月28日
Antoine J. -P. Tixier
10+阅读 · 2018年8月30日
Dinghan Shen,Martin Renqiang Min,Yitong Li,Lawrence Carin
5+阅读 · 2018年8月30日
A Survey on Deep Transfer Learning
Chuanqi Tan,Fuchun Sun,Tao Kong,Wenchang Zhang,Chao Yang,Chunfang Liu
10+阅读 · 2018年8月6日
Chung-Wei Lee,Wei Fang,Chih-Kuan Yeh,Yu-Chiang Frank Wang
7+阅读 · 2018年5月26日
Andrew K. Lampinen,James L. McClelland
5+阅读 · 2017年10月27日
Top