arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.13832cs.CLcs.AIcs.NE
收藏

基于进化的自然语言处理方法

Towards an evolutionary-based approach for natural language processing

Università degli Studi di Trieste(的里雅斯特大学);University of Zagreb(萨格勒布大学);Delft University of Technology(代尔夫特理工大学);Universidade Nova de Lisboa(新里斯本大学);NOVA Information Management School (NOVA IMS)(新信息管理学院(NOVA IMS))

Luca Manzoni, Domagoj Jakobovic, Luca Mariot, Stjepan Picek, Mauro Castelli

摘要:

与自然语言处理(NLP)相关的任务最近已经成为机器学习社区的大型研究努力的焦点。人们对这一领域兴趣的增加主要是由于深度学习方法的成功。然而,遗传编程(GP)在NLP任务方面并没有受到关注。在这里,我们提出了第一个概念验证,将GP与成熟的NLP工具word2vec相结合,用于下一个单词预测任务。其主要思想是,一旦单词被移动到向量空间中,传统的GP运算符就可以成功地处理向量,从而产生有意义的单词作为输出。为了评估这种方法的适用性,我们进行了一组现有的报纸标题的实验评估。从这个(预)训练阶段产生的个体可以作为其他NLP任务的初始种群,例如句子生成,这将是未来研究的重点,可能采用对抗性共同进化方法。

英文摘要:

Tasks related to Natural Language Processing (NLP) have recently been the focus of a large research endeavor by the machine learning community. The increased interest in this area is mainly due to the success of deep learning methods. Genetic Programming (GP), however, was not under the spotlight with respect to NLP tasks. Here, we propose a first proof-of-concept that combines GP with the well established NLP tool word2vec for the next word prediction task. The main idea is that, once words have been moved into a vector space, traditional GP operators can successfully work on vectors, thus producing meaningful words as the output. To assess the suitability of this approach, we perform an experimental evaluation on a set of existing newspaper headlines. Individuals resulting from this (pre-)training phase can be employed as the initial population in other NLP tasks, like sentence generation, which will be the focus of future investigations, possibly employing adversarial co-evolutionary approaches.

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。

↑