· 2014
Convolutional Neural Networks for Sentence Classification
- 13,859citations
- 2014year
Short summary
A simple Convolutional Neural Network (CNN) using pre-trained word vectors achieves state-of-the-art results on 4 out of 7 sentence classification tasks, including sentiment analysis and question classification.
AI-generated from the title and abstract; the full text is not read.
Key points
- Simple CNNs with static, pre-trained word vectors achieve strong results on sentence classification.
- Fine-tuning word vectors for task-specific learning further improves CNN performance.
- A modified architecture allows the combined use of task-specific and static vectors.
- The proposed CNN models set new state-of-the-art on 4 out of 7 evaluated benchmarks.
AI-generated from the title and abstract; the full text is not read.
Abstract
We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific vectors through fine-tuning offers further gains in performance. We additionally propose a simple modification to the architecture to allow for the use of both task-specific and static vectors. The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification.
The authors' abstract, as published at the source., 2014 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science