Abstract
We introduce Texar, an open-source toolkit aiming to support the broad set of text generation tasks that transforms any inputs into natural language, such as machine translation, summarization, dialog, content manipulation, and so forth. With the design goals of modularity, versatility, and extensibility in mind, Texar extracts common patterns underlying the diverse tasks and methodologies, creates a library of highly reusable modules and functionalities, and allows arbitrary model architectures and algorithmic paradigms. In Texar, model architecture, losses, and learning processes are fully decomposed. Modules at high concept level can be freely assembled or plugged in/swapped out. These features make Texar particularly suitable for researchers and practitioners to do fast prototyping and experimentation, as well as foster technique sharing across different text generation tasks. We provide case studies to demonstrate the use and advantage of the toolkit. Texar is released under Apache license 2.0 at https://github.com/asyml/texar.
Abstract (translated)
我们介绍Texar,这是一个开源工具包,旨在支持广泛的文本生成任务,将任何输入转换为自然语言,如机器翻译,摘要,对话,内容操作等。考虑到模块化,多功能性和可扩展性的设计目标,Texar提取了各种任务和方法的基本模式,创建了一个高度可重用的模块和功能库,并允许任意模型架构和算法范例。在Texar中,模型架构,损失和学习过程被完全分解。高概念级别的模块可以自由组装或插入/换出。这些特性使Texar特别适合研究人员和从业人员进行快速原型设计和实验,以及促进不同文本生成任务之间的技术共享。我们提供案例研究来证明该工具包的使用和优势。 Texar在Apache许可2.0下发布,网址为https://github.com/asyml/texar。
URL
https://arxiv.org/abs/1809.00794