Robust Text Classification for Sparsely Labelled Data Using Multi-level Embeddings
The conventional solution for handling sparsely labelled data is extensive feature engineering. This is time consuming and task and domain specific. We present a novel approach for learning embedded features that aims to alleviate this problem. Our approach jointly learns embeddings at different levels of granularity (word, sentence and document) along with the class labels. The intuition is that topic semantics represented by embeddings at multiple levels results in better classification. We evaluate this approach in unsupervised and semi-supervised settings on two sparsely labelled classification tasks, outperforming the handcrafted models and several embedding baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationFeature EngineeringGeneral ClassificationNamed Entity Recognition (NER)Sentencetext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels
In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It …
ClusteringSemi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation
To obtain 3D annotations, we are restricted to controlled environments or synthetic datasets, leading us to 3D datasets with less generalizability to real-world scenarios. To tackle this issue in the context of semi-supe…
Pose EstimationSparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
Recent Image-to-Image Translation algorithms have achieved significant progress in neural style transfer and image attribute manipulation tasks. However, existing approaches require exhaustively labelling training data, …
AttributeImage-to-Image TranslationMulti-Task LearningStyle Transfer+1Graph Convolutional Network for Swahili News Classification
This work empirically demonstrates the ability of Text Graph Convolutional Network (Text GCN) to outperform traditional natural language processing benchmarks for the task of semi-supervised Swahili news classification. …
ClassificationGeneral ClassificationNews ClassificationSemi-unsupervised Learning of Human Activity using Deep Generative Models
We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able …
ClassificationGeneral ClassificationTime SeriesTime Series Analysis+2