arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1610.01588cs.CL
收藏

用于领域自适应的神经结构对应学习

Neural Structural Correspondence Learning for Domain Adaptation

Technion, IIT(以色列理工学院)

Yftah Ziser, Roi Reichart

摘要:

领域自适应是一个基本的NLP挑战,它将模型从富含标记训练数据的领域调整到缺乏此类数据的领域。我们介绍了一种神经网络模型,该模型通过表示学习将领域自适应的两个突出研究方向的思想结合在一起:结构对应学习(SCL,(Blitzer et al.,2006))和自动编码器神经网络。特别地,我们的模型是一个三层神经网络,它学习将输入示例的非枢轴特征编码为低维表示,以便可以从该表示中解码示例中枢轴特征(在两个域中都很突出并为NLP任务传递有用信息的特征)的存在。低维表示,然后采用在一个学习算法的任务。此外,我们展示了如何将预训练的词嵌入注入到我们的模型中,以提高具有相似枢轴特征的示例的泛化能力。关于跨领域产品情感分类的任务(Blitzer等人,2007),由12个域对组成,我们的模型优于SCL和边缘化堆叠去噪自动编码器(MSDA,(Chen et al.,2012年))方法分别为3.77%和2.17%,平均跨域对。

英文摘要:

Domain adaptation, adapting models from domains rich in labeled training data to domains poor in such data, is a fundamental NLP challenge. We introduce a neural network model that marries together ideas from two prominent strands of research on domain adaptation through representation learning: structural correspondence learning (SCL, (Blitzer et al., 2006)) and autoencoder neural networks. Particularly, our model is a three-layer neural network that learns to encode the nonpivot features of an input example into a low-dimensional representation, so that the existence of pivot features (features that are prominent in both domains and convey useful information for the NLP task) in the example can be decoded from that representation. The low-dimensional representation is then employed in a learning algorithm for the task. Moreover, we show how to inject pre-trained word embeddings into our model in order to improve generalization across examples with similar pivot features. On the task of cross-domain product sentiment classification (Blitzer et al., 2007), consisting of 12 domain pairs, our model outperforms both the SCL and the marginalized stacked denoising autoencoder (MSDA, (Chen et al., 2012)) methods by 3.77% and 2.17% respectively, on average across domain pairs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑