We focus on morphological inflection in out-of-vocabulary (OOV) conditions, an under-researched subtask in which state-of-the-art systems usually are less effective. We developed three systems: a retrograde model and two sequence-to-sequence (seq2seq) models based on LSTM and Transformer. For testing in OOV conditions, we automatically extracted a large dataset of nouns in the morphologically rich Czech language, with lemma-disjoint data splits, and we further manually annotated a real-world OOV dataset of neologisms. In the standard OOV conditions, Transformer achieves the best results, with increasing performance in ensemble with LSTM, the retrograde model and SIGMORPHON baselines. On the real-world OOV dataset of neologisms, the retrograde model outperforms all neural models. Finally, our seq2seq models achieve state-of-the-art results in 9 out of 16 languages from SIGMORPHON 2022 shared task data in the OOV evaluation (feature overlap) in the large data condition. We release the Czech OOV Inflection Dataset for rigorous evaluation in OOV conditions. Further, we release the inflection system with the seq2seq models as a ready-to-use Python library.

翻译：本文聚焦于词汇外（OOV）条件下的形态屈折变化任务，这是一个研究不足的子任务，现有最先进系统在此条件下通常效果欠佳。我们开发了三个系统：一个逆向模型以及两个基于LSTM和Transformer的序列到序列（seq2seq）模型。为测试OOV条件，我们自动提取了一个大规模、形态丰富的捷克语名词数据集，采用词元不相交的数据划分方式，并进一步人工标注了一个真实世界的OOV新词数据集。在标准OOV条件下，Transformer模型取得了最佳结果，且与LSTM、逆向模型及SIGMORPHON基线模型集成后性能持续提升。在真实世界的新词OOV数据集上，逆向模型的表现优于所有神经网络模型。最后，我们的seq2seq模型在SIGMORPHON 2022共享任务数据的16种语言中，于大数据条件下的OOV评估（特征重叠）中，在9种语言上取得了最先进的结果。我们发布了捷克语OOV屈折变化数据集以支持严格的OOV条件评估。此外，我们将包含seq2seq模型的屈折变化系统发布为即用型Python库。