Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
复制标题
DOI：
--
复制
发表时间：
2011-07
影响因子：
4.4
通讯作者：
R. Socher;Jeffrey Pennington;E. Huang;A. Ng;Christopher D. Manning
中科院分区：
文献类型：
--
作者：
R. Socher;Jeffrey Pennington;E. Huang;A. Ng;Christopher D. Manning
我们介绍了一种基于递归自动编码器的机器学习框架，用于句子级别的情感标签分布预测。我们的方法学习多词短语的向量空间表示。在情感预测任务中，这些表示在常用数据集上的表现优于其他最先进的方法，例如电影评论，而不使用任何预定义的情感词汇或极性转换规则。我们还评估了该模型基于体验项目中的供词在新数据集上预测情绪分布的能力。数据集由用多个标签注释的个人用户故事组成，当这些标签聚合在一起时，形成了一个多项分布，可以捕捉情绪反应。与几个竞争性基线相比，我们的算法可以更准确地预测这些标签上的分布。
We introduce a novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions. Our method learns vector space representations for multi-word phrases. In sentiment prediction tasks these representations outperform other state-of-the-art approaches on commonly used datasets, such as movie reviews, without using any pre-defined sentiment lexica or polarity shifting rules. We also evaluate the model's ability to predict sentiment distributions on a new dataset based on confessions from the experience project. The dataset consists of personal user stories annotated with multiple labels which, when aggregated, form a multinomial distribution that captures emotional reactions. Our algorithm can more accurately predict distributions over such labels compared to several competitive baselines.