AllenNLP: A Deep Semantic Natural Language Processing Platform
Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, Luke Zettlemoyer Allen Institute for Artificial Intelligence
Abstract
Modern natural language processing (NLP) research requires writing code. Ideally this code would provide a precise definition of the approach, easy repeatability of results, and a basis for extending the research. However, many research codebases bury high-level parameters under implementation details, are challenging to run and debug, and are difficult enough to extend that they are more likely to be rewritten. This paper describes AllenNLP, a library for applying deep learning methods to NLP research, which addresses these issues with easy-to-use command-line tools, declarative configuration-driven experiments, and modular NLP abstractions. AllenNLP has already increased the rate of research experimentation and the sharing of NLP components at the Allen Institute for Artificial Intelligence, and we are working to have the same impact across the field.
中文速览
自然语言处理（NLP）研究越来越依赖深度学习代码，但现有代码库往往把核心逻辑淹没在底层实现细节里，复现和扩展都极为困难。为此，Allen人工智能研究所推出了AllenNLP这一开源库，它基于PyTorch构建，通过声明式配置文件驱动实验、模块化的NLP抽象层（如统一的词向量嵌入、序列编码器接口），以及自动处理填充和掩码等繁琐细节，让研究者只需改一个配置文件就能切换模型架构或调整超参数。库中还内置了语义角色标注、机器阅读理解、文本蕴含、成分句法分析等多个达到当时最优水平的参考实现，并提供可交互的在线演示。这一工具已在内部显著提升了研究效率和成果复用率，对整个NLP社区而言，它大幅降低了高质量研究的门槛，让"把时间花在想法本身而非重复造轮子"成为可能。
原文 arXiv:1803.07640;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1803.07640v2