An unsupervised, entropy-guided, parsimonious segmentation method that beats BPE, unigram LM, and Morfessor on morphological gold standards and modestly improves word embeddings and language modeling.
Knet: A general framework for learning word embedding using morphological knowledge
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings
An unsupervised, entropy-guided, parsimonious segmentation method that beats BPE, unigram LM, and Morfessor on morphological gold standards and modestly improves word embeddings and language modeling.