Incorporating Latent Meanings of Morphological Compositions to Enhance Word Embeddings from cess meaning Watch Video

⏲ Duration: 11 min 73 sec
✓ Published: 20-Aug-2018

Description:
Traditional word embedding approaches learn semantic information at word level while ignoring the meaningful in-ternal structures of words like morphemes. Furthermore, existing morphology-based models directly incorporate morphemes to train word embeddings, but still neglect the latent meanings of morphemes. In this paper, we ex-plore to employ the latent meanings of morphological compositions of words to train and enhance word embeddings. Based on this purpose, we propose three Latent Meaning M