arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.08352cs.CL
收藏

从字符到单词再到介于两者之间:我们捕捉形态学了吗?

From Characters to Words to in Between: Do We Capture Morphology?

University of Edinburgh(爱丁堡大学)

Clara Vania, Adam Lopez

摘要:

单词可以通过组成子单词单元的表示来表示,诸如单词段、字符和/或字符n-gram。虽然这种表示是有效的,并可能捕捉到的词的形态学特征,他们没有被系统地比较,它是不明白他们如何与不同的形态类型学相互作用。在语言建模任务中,我们提出了系统地改变(1)表征的基本单位,(2)这些表征的组成,以及(3)建模语言的形态类型学的实验。我们的研究结果扩展了以前的研究结果,字符表示是有效的类型学,我们发现,以前未研究的组合组成的字符trigram表示与双LSTM优于大多数其他。但我们也发现了改进的空间:没有一个字符级别的模型与能够获得真正形态分析的模型的预测准确性相匹配,即使是从一个数量级的数据中学习。

英文摘要:

Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they have not been systematically compared, and it is not understood how they interact with different morphological typologies. On a language modeling task, we present experiments that systematically vary (1) the basic unit of representation, (2) the composition of these representations, and (3) the morphological typology of the language modeled. Our results extend previous findings that character representations are effective across typologies, and we find that a previously unstudied combination of character trigram representations composed with bi-LSTMs outperforms most others. But we also find room for improvement: none of the character-level models match the predictive accuracy of a model with access to true morphological analyses, even when learned from an order of magnitude more data.

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。

↑