Unsupervised Document Embedding With CNNs
원문 초록
We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a convolutional neural network (CNN) embedding model. Our CNN architecture is fully parallelizable resulting in over 10x speedup in inference time over RNN models. Parallelizable architecture enables to train deeper models where each successive layer has increasingly larger receptive field and models longer range semantic structure within the document. We additionally propose a fully unsupervised learning algorithm to train this model based on stochastic forward prediction. Empirical results on two public benchmarks show that our approach produces comparable to state-of-the-art accuracy at a fraction of computational cost.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
QAEncoder: Towards Aligned Representation Learning in Question Answering System
ARAGOG: Advanced RAG Output Grading
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification
Facilitating Interdisciplinary Knowledge Transfer with Research Paper Recommender Systems
Approach to Predicting News -- A Precise Multi-LSTM Network With BERT
BERTopic: Neural topic modeling with a class-based TF-IDF procedure
토론
이 논문과 연결된 포럼 글이 아직 없습니다.