Attention-free encoder decoder for morphological processing
Ștefan Daniel Dumitrescu, Tiberiu Boroş · Proceedings of the · 2018
We present RACAI's Entry for the CoNLL-SIGMORPHON 2018 shared task on universal morphological reinflection.The system is based on an attention-free encoder-decoder neural architecture with a bidirectional LSTM for encoding the input sequence and a unidirectional LSTM for decoding and producing the output.Instead of directly applying a sequence-to-sequence model at character-level we use a dynamic algorithm to align the input and output sequences.Based on these alignments we produce a series of special symbols which are similar to those of a finite-statetransducer (FST).