Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
复制标题
DOI：
10.18653/v1/p19-1152
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
P. Liang;Zhun Liu;Yao-Hung Hubert Tsai;Qibin Zhao;R. Salakhutdinov;Louis-Philippe Morency
中科院分区：
文献类型：
--
作者：
P. Liang;Zhun Liu;Yao-Hung Hubert Tsai;Qibin Zhao;R. Salakhutdinov;Louis-Philippe Morency
人们对多模态语言处理越来越感兴趣，包括多模态对话、问答、情感分析和语音识别。然而，自然发生的多模态数据往往是不完美的，因为不完美的模态，缺失的条目或噪声损坏。为了解决这些问题，我们提出了一种基于张量秩最小化的正则化方法。我们的方法是基于观察到高维多模态时间序列数据经常表现出跨时间和模态的相关性，从而导致低秩张量表示。然而，噪声或不完整值的存在打破了这些相关性，并导致更高秩的张量表示。我们设计了一个模型来学习这种张量表示，并有效地正则化它们的秩。在多模态语言数据上的实验表明，我们的模型在不同程度的缺陷上都取得了很好的效果。
There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a result of imperfect modalities, missing entries or noise corruption. To address these concerns, we present a regularization method based on tensor rank minimization. Our method is based on the observation that high-dimensional multimodal time series data often exhibit correlations across time and modalities which leads to low-rank tensor representations. However, the presence of noise or incomplete values breaks these correlations and results in tensor representations of higher rank. We design a model to learn such tensor representations and effectively regularize their rank. Experiments on multimodal language data show that our model achieves good results across various levels of imperfection.