arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.09439cs.CL
收藏

风格感知的Sequence-to-Sequence模型的先验注意力

Prior Attention for Style-aware Sequence-to-Sequence Models

Ghent University(根特大学);imec(imec校际微电子中心)

Lucas Sterckx, Johannes Deleu, Chris Develder, Thomas Demeester

摘要:

我们扩展序列到序列模型的可能性,以控制所生成的输出的特性或风格,通过注意力,这是从一个潜在的代码向量的先验(解码前)。在训练了初始的基于注意力的序列到序列模型之后,我们使用基于输入序列的表示和潜在代码向量空间的变分自动编码器来生成注意力矩阵。通过在解码期间从该潜在空间的特定区域采样代码向量,并在seq 2seq模型中施加由其生成的先前注意力,可以将输出转向具有某些属性。这是证明了句子简化的任务,其中的潜在代码向量允许控制输出长度和词汇简化,并使微调,以优化不同的评估指标。

英文摘要:

We extend sequence-to-sequence models with the possibility to control the characteristics or style of the generated output, via attention that is generated a priori (before decoding) from a latent code vector. After training an initial attention-based sequence-to-sequence model, we use a variational auto-encoder conditioned on representations of input sequences and a latent code vector space to generate attention matrices. By sampling the code vector from specific regions of this latent space during decoding and imposing prior attention generated from it in the seq2seq model, output can be steered towards having certain attributes. This is demonstrated for the task of sentence simplification, where the latent code vector allows control over output length and lexical simplification, and enables fine-tuning to optimize for different evaluation metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑