arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.07091cs.CL
收藏

INFODENS:一个开源的文本表示学习框架

INFODENS: An Open-source Framework for Learning Text Representations

Saarland University(萨尔大学);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI))

Ahmad Taie, Raphael Rubino, Josef van Genabith

摘要:

表示学习方法的出现使各种语言任务的性能大幅提高,减轻了对手动特征工程的需求。虽然工程表征通常基于某种语言理解,因此更容易解释,但学习表征更难解释。从经验上研究这两种方法的互补性可以提供更多的语言见解,这将有助于在可解释性和性能之间达成更好的妥协。我们提出了信息,一个框架,学习和工程表示的文本分类任务的背景下。它旨在简化特征工程的任务,并为提取学习特征和结合这两种方法提供基础。INFODENS是灵活的,可扩展的,具有较短的学习曲线,并且易于与许多可用的和广泛使用的自然语言处理工具集成。

英文摘要:

The advent of representation learning methods enabled large performance gains on various language tasks, alleviating the need for manual feature engineering. While engineered representations are usually based on some linguistic understanding and are therefore more interpretable, learned representations are harder to interpret. Empirically studying the complementarity of both approaches can provide more linguistic insights that would help reach a better compromise between interpretability and performance. We present INFODENS, a framework for studying learned and engineered representations of text in the context of text classification tasks. It is designed to simplify the tasks of feature engineering as well as provide the groundwork for extracting learned features and combining both approaches. INFODENS is flexible, extensible, with a short learning curve, and is easy to integrate with many of the available and widely used natural language processing tools.

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。

↑