arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.11037cs.CLcs.LG
收藏

使用成对马尔可夫链实现高度快速的文本分割

Highly Fast Text Segmentation With Pairwise Markov Chains

SAMOVAR, Telecom SudParis Institut Polytechnique de Paris(SAMOVAR,电信南巴黎高等学院)

Elie Azeraf, Emmanuel Monfrini, Emmanuel Vignon, Wojciech Pieczynski

AI总结:

本文针对NLP模型依赖额外数据导致计算成本高的问题,探索成对马尔可夫链(PMC)用于文本分割任务,在无额外数据下取得与CRF相当的性能且训练时间缩短30倍。

摘要:

自然语言处理(NLP)模型的当前趋势是使用越来越多的额外数据来构建尽可能好的模型。这意味着更高的计算成本和训练时间、部署困难,以及对这些模型碳足迹的担忧,这在未来揭示了一个关键问题。针对这一趋势,我们的目标是开发不需要额外数据并最小化训练时间的NLP模型。为此,在本文中,我们探索了马尔可夫链模型、隐马尔可夫链(HMC)和成对马尔可夫链(PMC),用于NLP分割任务。我们将这些模型应用于三个经典应用:词性标注、命名实体识别和分块。我们开发了一种原创方法,使这些模型适应文本分割的特定挑战,从而在非常短的训练和执行时间内获得相关性能。PMC取得了与条件随机场(CRF)相当的结果,CRF是在不使用额外数据时用于这些任务的最常用模型之一。此外,PMC的训练时间比CRF短30倍,鉴于我们的目标,这验证了该模型。

英文摘要:

Natural Language Processing (NLP) models' current trend consists of using increasingly more extra-data to build the best models as possible. It implies more expensive computational costs and training time, difficulties for deployment, and worries about these models' carbon footprint reveal a critical problem in the future. Against this trend, our goal is to develop NLP models requiring no extra-data and minimizing training time. To do so, in this paper, we explore Markov chain models, Hidden Markov Chain (HMC) and Pairwise Markov Chain (PMC), for NLP segmentation tasks. We apply these models for three classic applications: POS Tagging, Named-Entity-Recognition, and Chunking. We develop an original method to adapt these models for text segmentation's specific challenges to obtain relevant performances with very short training and execution times. PMC achieves equivalent results to those obtained by Conditional Random Fields (CRF), one of the most applied models for these tasks when no extra-data are used. Moreover, PMC has training times 30 times shorter than the CRF ones, which validates this model given our objectives.

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。

↑