Text Emotion Distribution Learning from Small Sample: A Meta-Learning Approach
Text Emotion Distribution Learning from Small Sample: A Meta-Learning Approach
复制标题
DOI：
10.18653/v1/d19-1408
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Zhenjie Zhao;Xiaojuan Ma
中科院分区：
文献类型：
--
作者：
Zhenjie Zhao;Xiaojuan Ma
文本情感分布学习（EDL）旨在开发能够预测句子在一组情感类别中的强度值的模型。现有的基于监督学习的方法需要大量标记良好的训练数据，由于对细粒度情感强度的感知不一致，很难获得这些数据。在本文中，我们提出了一种元学习方法来学习文本情感分布从一个小样本。具体来说，我们建议通过张量分解来学习低秩句子嵌入，以捕获它们的上下文语义相似性，并使用嵌入空间中每个句子的K-最近邻（KNN）来生成样本聚类。然后，我们训练一个元学习器，它可以适应新的数据，只有少数几个训练样本的集群，并进一步适合元学习器上的一个测试样本的知识神经网络的EDL。通过这种方式，我们有效地增强了模型在小样本下的学习能力。为了证明性能，我们将所提出的方法与广泛使用的EDL数据集上的最先进的EDL方法进行了比较：SemEval 2007任务14（Strapparava和Mihalcea，2007）。实验结果表明，该方法在小样本情感分布学习方面具有优越性。
Text emotion distribution learning (EDL) aims to develop models that can predict the intensity values of a sentence across a set of emotion categories. Existing methods based on supervised learning require a large amount of well-labelled training data, which is difficult to obtain due to inconsistent perception of fine-grained emotion intensity. In this paper, we propose a meta-learning approach to learn text emotion distributions from a small sample. Specifically, we propose to learn low-rank sentence embeddings by tensor decomposition to capture their contextual semantic similarity, and use K-nearest neighbors (KNNs) of each sentence in the embedding space to generate sample clusters. We then train a meta-learner that can adapt to new data with only a few training samples on the clusters, and further fit the meta-learner on KNNs of a testing sample for EDL. In this way, we effectively augment the learning ability of a model on the small sample. To demonstrate the performance, we compare the proposed approach with state-of-the-art EDL methods on a widely used EDL dataset: SemEval 2007 Task 14 (Strapparava and Mihalcea, 2007). Results show the superiority of our method on small-sample emotion distribution learning.