KNET: A General Framework for Learning Word Embedding Using Morphological Knowledge

doi:10.1145/2797137

KNET: A General Framework for Learning Word Embedding Using Morphological Knowledge

2015-08-24

8

PRE

AI

DOI：10.1145/2797137

Original request for help

Save

Abstract

En 中文

Neural network techniques are widely applied to obtain high-quality distributed representations of words (i.e., word embeddings) to address text mining, information retrieval, and natural language processing tasks. Most recent efforts have proposed several efficient methods to learn word embeddings from context such that they can encode both semantic and syntactic relationships between words. However, it is quite challenging to handle unseen or rare words with insufficient context. Inspired by the study on the word recognition process in cognitive psychology, in this article, we propose to take advantage of seemingly less obvious but essentially important morphological knowledge to address these challenges. In particular, we introduce a novel neural network architecture called KNET that leverages both words' contextual information and morphological knowledge to learn word embeddings. Meanwhile, this new learning architecture is also able to benefit from noisy knowledge and balance between contextual information and morphological knowledge. Experiments on an analogical reasoning task and a word similarity task both demonstrate that the proposed KNET framework can greatly enhance the effectiveness of word embeddings.

Keywords:

Neural network

word embedding

morphological knowledge

KNET: A General Framework for Learning Word Embedding Using Morphological Knowledge

Abstract

AI Summary

Journal

Organization