OOVs in the Spotlight: How to Inflect them?

arXiv:2404.08974v1 Announce Type: new
Abstract: 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 …

abstract art arxiv cs.cl focus inflection in the spotlight lstm seq2seq spotlight state systems testing them transformer type