Hierarchical Quantized Representations for Script Generation
Hierarchical Quantized Representations for Script Generation
复制标题
脚本生成的分层量化表示
DOI：
10.18653/v1/d18-1413
复制
发表时间：
2018
影响因子：
19.5
通讯作者：
N. Chambers
中科院分区：
文献类型：
--
作者：
Noah Weber;L. Shekhar;Niranjan Balasubramanian;N. Chambers
脚本定义了有关日常场景（例如去餐馆）预计如何展开的知识。学习脚本的挑战之一是知识的层次性。例如，被捕的嫌疑人可能会认罪或认罪，然后预计会发生截然不同的事件轨迹。为了捕获此类信息，我们提出了一种自动编码器模型，其潜在空间由分类变量的层次结构定义。我们利用最近提出的基于矢量量化的方法，该方法允许连续嵌入与每个潜在变量值相关联。这允许解码器通过关注给定设置的值嵌入来软性地决定以潜在层次结构的哪些部分为条件。我们的模型有效地编码和生成脚本，在几个标准任务上优于最近的基于语言建模的方法，并且与之前基于语言建模的方法相比，自动编码器模型能够实现显着降低的困惑度分数。
Scripts define knowledge about how everyday scenarios (such as going to a restaurant) are expected to unfold. One of the challenges to learning scripts is the hierarchical nature of the knowledge. For example, a suspect arrested might plead innocent or guilty, and a very different track of events is then expected to happen. To capture this type of information, we propose an autoencoder model with a latent space defined by a hierarchy of categorical variables. We utilize a recently proposed vector quantization based approach, which allows continuous embeddings to be associated with each latent variable value. This permits the decoder to softly decide what portions of the latent hierarchy to condition on by attending over the value embeddings for a given setting. Our model effectively encodes and generates scripts, outperforming a recent language modeling-based method on several standard tasks, and allowing the autoencoder model to achieve substantially lower perplexity scores compared to the previous language modeling-based method.