In this paper, we show the progress for Arabic speech recognition by incorporating contextual information into the process of morphological decomposition. The new approach achieves lower out-of-vocabulary and word error rates when compared to our previous work, in which the morphological decomposition relies on word-level information only. We also describe how the vocalization procedure is impr...

This paper presents initial experiments in data-driven morphological analysis for Finnish using deep learning methods. Our system uses a character based bidirectional LSTM and pretrained word embeddings to predict a set of morphological analyses for an input word form. We present experiments on morphological analysis for Finnish. We learn to mimic the output of the OMorFi analyzer on the Finnis...

This paper presents a joint model for performing unsupervised morphological analysis on words, and learning a character-level composition function from morphemes to word embeddings. Our model splits individual words into segments, and weights each segment according to its ability to predict context words. Our morphological analysis is comparable to dedicated morphological analyzers at the task ...

Arabic has a very complex morphological system, though a very structured one. Character patterns are often indicative of word class and word segmentation. In this paper, we e xplore a novel approach to Arabic word segmentation and part-of-speech tagging relying on character information. The approach is lexicon-free and does not require any morphological analysis, eliminat ing the factor of dict...