Neural Headline Generation with Minimum Risk Training
今天分享的paper是Neural Headline Generation with Minimum Risk Training。 本文通过将评价指标融入目标函数来训练模型，在中文和英文数据集上均取得了超过之前所有模型的结果。结果一点也不意外，因为传统的MLE并不是以ROUGE评价指标最大为目标函数，而本文的方法针对了评价指标来做文章，一定会得到不错的结果。反过来，我们需要思考一个问题，如果文本摘
相关文章
- 1. 【读】seq2seq——（6）Neural Headline Generation with Minimum Risk Training
- 2. Text Generation With LSTM Recurrent Neural Networks in Python with Keras
- 3. Neural Response Generation via GAN with an Approximate Embedding Layer
- 4. BinaryConnect： Training Deep Neural Networks with binary weights during propagations
- 5. TRAINING DEEP NEURAL NETWORKS WITH LOW PRECISION MULTIPLICATIONS
- 6. Synchronous Bidirectional Inference for Neural Sequence Generation
- 7. Training Neural Networks, part I
- 8. Training Recurrent Neural Network
- 9. （转）A Recipe for Training Neural Networks
- 10. AAAI2018-Long Text Generation via Adversarial Training with Leaked Information论文笔记
- 更多相关文章...
- • XSLT
- • Docker 容器连接 - Docker教程
- • 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
- • Composer 安装与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 【读】seq2seq——（6）Neural Headline Generation with Minimum Risk Training
- 2. Text Generation With LSTM Recurrent Neural Networks in Python with Keras
- 3. Neural Response Generation via GAN with an Approximate Embedding Layer
- 4. BinaryConnect： Training Deep Neural Networks with binary weights during propagations
- 5. TRAINING DEEP NEURAL NETWORKS WITH LOW PRECISION MULTIPLICATIONS
- 6. Synchronous Bidirectional Inference for Neural Sequence Generation
- 7. Training Neural Networks, part I
- 8. Training Recurrent Neural Network
- 9. （转）A Recipe for Training Neural Networks
- 10. AAAI2018-Long Text Generation via Adversarial Training with Leaked Information论文笔记