MORSE: Semantic-ally Drive-n MORpheme SEgment-er
This addresses morpheme segmentation for NLP, introducing a novel approach that considers syntactico-semantic information, though it is domain-specific.
The paper tackles morpheme segmentation by using morpho-syntactic regularities from word representations and orthographic features, achieving state-of-the-art results across datasets.
We present in this paper a novel framework for morpheme segmentation which uses the morpho-syntactic regularities preserved by word representations, in addition to orthographic features, to segment words into morphemes. This framework is the first to consider vocabulary-wide syntactico-semantic information for this task. We also analyze the deficiencies of available benchmarking datasets and introduce our own dataset that was created on the basis of compositionality. We validate our algorithm across datasets and present state-of-the-art results.