Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings
This addresses the issue of semantic granularity in text-mining for languages and corpora with subword structures, offering a domain-specific improvement in natural language processing.
The paper tackles the problem of poor word embeddings for infrequent and out-of-vocabulary words by proposing MorphMine, an unsupervised morpheme segmentation method that hierarchically segments words into the fewest morphemes, leading to improved embedding quality on various evaluations and a language modeling task.
Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures. Word-level analysis cannot leverage the semantic information present in such subword structures. With regard to word embedding techniques, this leads to not only poor embeddings for infrequent words in long-tailed text corpora but also weak capabilities for handling out-of-vocabulary words. In this paper we propose MorphMine for unsupervised morpheme segmentation. MorphMine applies a parsimony criterion to hierarchically segment words into the fewest number of morphemes at each level of the hierarchy. This leads to longer shared morphemes at each level of segmentation. Experiments show that MorphMine segments words in a variety of languages into human-verified morphemes. Additionally, we experimentally demonstrate that utilizing MorphMine morphemes to enrich word embeddings consistently improves embedding quality on a variety of of embedding evaluations and a downstream language modeling task.