Morphological Inflection is the task of generating a target (inflected form) word from a source word (base form), given a morphological attribute, e.g. number, tense, and person etc. It is useful for alleviating data sparsity issues in translating morphologically rich languages. The transformation from a base form to an inflected form usually includes concatenating the base form with a prefix or a suffix and substituting some characters. For example, the inflected form of a Finnish stem eläkeikä (retirement age) is eläkeiittä when the case is abessive and the number is plural.
We present a neural model for morphological inflection generation which employs a hard attention mechanism, inspired by the nearly-monotonic alignment commonly found between the characters in a word and the characters in its inflection.
Morphological inflection generation is the task of generating the inflected form of a given lemma corresponding to a particular linguistic transformation.
In an empirical study, we uncover that, in contrast to recurrent sequence-to-sequence models, the batch size plays a crucial role in the performance of the transformer on character-level tasks, and we show that with a large enough batch size, the transformer does indeed outperform recurrent models.
Our models achieve state-of-the-art performance on morphological inflection.
In this paper we show that a simple beam approximation of the joint distribution between attention and output is an easy, accurate, and efficient attention mechanism for sequence to sequence learning.
Recent years have seen exceptional strides in the task of automatic morphological inflection generation.
Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic.
We introduce SimpleNLG-ZH, a realisation engine for Mandarin that follows the software design paradigm of SimpleNLG (Gatt and Reiter, 2009).