Aspect-augmented Adversarial Networks for Domain Adaptation
arXiv:1701.00188
Abstract
We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain. Rather than training on target labels, we use a few keywords pertaining to source and target aspects indicating sentence relevance instead of document class labels. Documents are encoded by learning to embed and softly select relevant sentences in an aspect-dependent manner. A shared classifier is trained on the source encoded documents and labels, and applied to target encoded documents. We ensure transfer through aspect-adversarial training so that encoded documents are, as sets, aspect-invariant. Experimental results demonstrate that our approach outperforms different baselines and model variants on two datasets, yielding an improvement of 27% on a pathology dataset and 5% on a review dataset.
arXiv commentTACL
References in corpus (11)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Domain Separation Networks
- From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
- Unsupervised Cross-Domain Image Generation
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
- Long Short-Term Memory-Networks for Machine Reading
- Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
- Rationale-Augmented Convolutional Neural Networks for Text Classification
Cited by in corpus (8)
- Adversarial Learning for Neural Dialogue Generation
- GraphGAN: Graph Representation Learning with Generative Adversarial Nets
- On Learning Invariant Representation for Domain Adaptation
- Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
- Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
- Adversarial Learning for Chinese NER from Crowd Annotations
- Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification
- Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval