TAMS:翻译辅助的形态学切分
TAMS: Translation-Assisted Morphological Segmentation
AI总结:
针对语言记录中规范形态学切分训练数据稀缺而翻译数据丰富的问题,提出利用预训练单语模型翻译表示的字符级序列到序列模型,在超低资源设定下优于基线。
摘要:
规范形态学切分是将词分析为其构成语素的规范(即底层)形式的过程。这是语言记录中的一项核心任务,NLP系统有潜力大幅加速该过程。但在典型的语言记录场景中,用于规范语素切分的训练数据稀缺,难以训练高质量模型。然而,翻译数据通常更为丰富。在本研究中,我们提出一种方法,试图在规范切分任务中利用这些翻译数据。我们提出一个字符级序列到序列模型,该模型将来自预训练高资源单语语言模型的翻译表示作为额外信号纳入其中。在超低资源设定下,我们的模型优于基线,但在数据量更大的训练划分上结果好坏参半。尽管仍需进一步研究使翻译在更高资源设定中发挥作用,但我们的模型在资源严重受限的设定中展现了潜力。
英文摘要:
Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes. This is a core task in language documentation, and NLP systems have the potential to dramatically speed up this process. But in typical language documentation settings, training data for canonical morpheme segmentation is scarce, making it difficult to train high quality models. However, translation data is often much more abundant, and, in this work, we present a method that attempts to leverage this data in the canonical segmentation task. We propose a character-level sequence-to-sequence model that incorporates representations of translations obtained from pretrained high-resource monolingual language models as an additional signal. Our model outperforms the baseline in a super-low resource setting but yields mixed results on training splits with more data. While further work is needed to make translations useful in higher-resource settings, our model shows promise in severely resource-constrained settings.
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。