arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.04022cs.CL
收藏

LSTM能学会达成一致吗?巴斯克案例

Can LSTM Learn to Capture Agreement? The Case of Basque

Bar Ilan University(巴伊兰大学);Higher School of Economics(高等经济学院);Indiana University(印第安纳大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所)

Shauli Ravfogel, Francis M. Tyers, Yoav Goldberg

摘要:

序列神经网络模型是各种自然语言处理(NLP)任务中的强大工具。这些模型的连续性提出了这样的问题:这些模型在多大程度上可以隐式地学习人类语言典型的层次结构,以及它们可以获得什么样的语法现象?我们专注于巴斯克语的协议预测任务,作为一个案例研究的任务,需要隐含的理解句子结构和收购一个复杂但一致的形态系统。从两个句法预测任务-动词数量预测和后缀恢复-分析实验结果,我们发现,顺序模型在巴斯克语中的协议预测表现得比以前的协议预测工作在英语的基础上预期的要差。基于诊断分类器的初步研究结果表明,该网络利用局部语义作为句子层次结构的代理。我们提出了巴斯克协议预测任务,作为具有挑战性的基准模型,试图学习人类语言的语言。

英文摘要:

Sequential neural networks models are powerful tools in a variety of Natural Language Processing (NLP) tasks. The sequential nature of these models raises the questions: to what extent can these models implicitly learn hierarchical structures typical to human language, and what kind of grammatical phenomena can they acquire? We focus on the task of agreement prediction in Basque, as a case study for a task that requires implicit understanding of sentence structure and the acquisition of a complex but consistent morphological system. Analyzing experimental results from two syntactic prediction tasks -- verb number prediction and suffix recovery -- we find that sequential models perform worse on agreement prediction in Basque than one might expect on the basis of a previous agreement prediction work in English. Tentative findings based on diagnostic classifiers suggest the network makes use of local heuristics as a proxy for the hierarchical structure of the sentence. We propose the Basque agreement prediction task as challenging benchmark for models that attempt to learn regularities in human language.

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。

↑