Neural Polysynthetic Language Modelling-猫眼课题宝

DOI：

发表时间：

2020-05

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Lane Schwartz;Francis M. Tyers;Lori S. Levin;Christo Kirov;Patrick Littell;Chi-kiu (羅致翹) Lo;Emily Prudhommeaux;Hyunji Hayley Park;K. Steimel;Rebecca Knowles;J. Micher;Lonny Strunk;Han Liu;Coleman Haley;Katherine J. Zhang;Robbie Jimmerson;Vasilisa Andriyanets;Aldrian Obaja Muis;Naoki Otani;J. Park;Zhisong Zhang

自然语言处理的研究通常假设，对英语和其他广泛使用的语言有效的方法是“语言不可知论”。在高资源语言中，特别是那些分析语言，一种常见的方法是将共同词根的形态不同变体视为完全独立的词类型。这假设每个词根的形态变化有限，并且大多数会出现在足够大的语料库中，因此模型可以充分学习关于每个形式的统计数据。当这些假设中的任何一个都不成立时，通常会使用词干提取、词形还原或子分词等方法，特别是在西班牙语或俄语等合成语言比英语有更多屈折变化的情况下。在文献中，芬兰语或土耳其语等语言被认为是挑战常见建模假设的复杂性的极端例子。然而，当考虑到世界上所有的语言时，芬兰语和土耳其语更接近平均水平。当我们考虑多合成语言（那些处于形态复杂性极端的语言）时，像词干提取、词形还原或子词建模这样的方法可能是不够的。这些语言具有非常高的hapax legomena数量，表明需要对单词进行适当的形态处理，否则模型不可能捕获足够的单词统计数据。我们研究了当前最先进的语言建模，机器翻译和文本预测的四个多合成语言：瓜拉尼，圣劳伦斯岛尤皮克，阿拉斯加中部尤皮克和因纽特人。然后，我们提出了一种新的语言建模框架，将有限状态形态分析器的知识表示与张量积表示相结合，以使神经语言模型能够处理各种类型的变体语言。

Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segmentation are often used when either of those assumptions do not hold, particularly in the case of synthetic languages like Spanish or Russian that have more inflection than English. In the literature, languages like Finnish or Turkish are held up as extreme examples of complexity that challenge common modelling assumptions. Yet, when considering all of the world's languages, Finnish and Turkish are closer to the average case. When we consider polysynthetic languages (those at the extreme of morphological complexity), approaches like stemming, lemmatization, or subword modelling may not suffice. These languages have very high numbers of hapax legomena, showing the need for appropriate morphological handling of words, without which it is not possible for a model to capture enough word statistics. We examine the current state-of-the-art in language modelling, machine translation, and text prediction for four polysynthetic languages: Guarani, St. Lawrence Island Yupik, Central Alaskan Yupik, and Inuktitut. We then propose a novel framework for language modelling that combines knowledge representations from finite-state morphological analyzers with Tensor Product Representations in order to enable neural language models capable of handling the full range of typologically variant languages.

Neural Polysynthetic Language Modelling

文献摘要

相似文献