Convolutional Neural Networks for Sentence Classification
Y. Kim. (2014)cite arxiv:1408.5882Comment: To appear in EMNLP 2014.
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.
Description
Convolutional Neural Networks for Sentence Classification
%0 Conference Paper
%1 kim2014convolutional
%A Kim, Yoon
%D 2014
%K classification cnn nlp seminar sentence ss2018 thema thema:cnn_kim
%T Convolutional Neural Networks for Sentence Classification
%U http://arxiv.org/abs/1408.5882
%X 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.
@inproceedings{kim2014convolutional,
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.},
added-at = {2018-01-17T13:54:08.000+0100},
author = {Kim, Yoon},
biburl = {https://www.bibsonomy.org/bibtex/22b2e4afbc7f9c81dbc79e2a80e461f3f/schwemmlein},
description = {Convolutional Neural Networks for Sentence Classification},
interhash = {5a18dcdef0fe1455c8d7d96cee67e2b6},
intrahash = {2b2e4afbc7f9c81dbc79e2a80e461f3f},
keywords = {classification cnn nlp seminar sentence ss2018 thema thema:cnn_kim},
note = {cite arxiv:1408.5882Comment: To appear in EMNLP 2014},
timestamp = {2018-03-19T19:31:41.000+0100},
title = {Convolutional Neural Networks for Sentence Classification},
url = {http://arxiv.org/abs/1408.5882},
year = 2014
}