arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07006cs.CLcs.AI
收藏

基于数据增强的形态学拐点三步训练方法

A Three Step Training Approach with Data Augmentation for Morphological Inflection

Budapest University of Technology and Economics(布达佩斯技术与经济大学)

Gabor Szolnok, Botond Barta, Dorina Lakatos, Judit Acs

摘要:

我们提交了SIGMORPHON 2021任务0第1部分,跨类型多样语言的泛化共享任务的BME提交。我们使用LSTM编码器-解码器模型,三步训练首先在所有语言上训练,然后在每个语言家族上进行微调,最后在单个语言上进行微调。在前两步中,我们使用不同类型的数据增强技术。我们的系统优于唯一的其他提交。虽然它仍然比组织者发布的Transformer基线更差,但我们的模型更简单,我们的数据增强技术很容易适用于新语言。我们进行了消融研究,并表明增强技术和三个训练步骤通常有帮助,但有时会产生负面影响。

英文摘要:

We present the BME submission for the SIGMORPHON 2021 Task 0 Part 1, Generalization Across Typologically Diverse Languages shared task. We use an LSTM encoder-decoder model with three step training that is first trained on all languages, then fine-tuned on each language families and finally finetuned on individual languages. We use a different type of data augmentation technique in the first two steps. Our system outperformed the only other submission. Although it remains worse than the Transformer baseline released by the organizers, our model is simpler and our data augmentation techniques are easily applicable to new languages. We perform ablation studies and show that the augmentation techniques and the three training steps often help but sometimes have a negative effect.

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。

↑