Morphological Inflection Generation Using Character Sequence to Sequence Learning
This work addresses the problem of generating inflected word forms for linguists and NLP practitioners, but it is incremental as it builds on existing neural encoder-decoder approaches.
The authors tackled morphological inflection generation by modeling it as a character sequence-to-sequence learning problem, achieving either better or comparable results to state-of-the-art models on seven datasets of morphologically rich languages.
Morphological inflection generation is the task of generating the inflected form of a given lemma corresponding to a particular linguistic transformation. We model the problem of inflection generation as a character sequence to sequence learning problem and present a variant of the neural encoder-decoder model for solving it. Our model is language independent and can be trained in both supervised and semi-supervised settings. We evaluate our system on seven datasets of morphologically rich languages and achieve either better or comparable results to existing state-of-the-art models of inflection generation.