%0 Conference Proceedings
%T Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics
%A Zhao, Zhe
%A Liu, Tao
%A Li, Shen
%A Li, Bofang
%A Du, Xiaoyong
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F zhao-etal-2017-ngram2vec
%X The existing word representation methods mostly limit their information source to word co-occurrence statistics. In this paper, we introduce ngrams into four representation methods: SGNS, GloVe, PPMI matrix, and its SVD factorization. Comprehensive experiments are conducted on word analogy and similarity tasks. The results show that improved word representations are learned from ngram co-occurrence statistics. We also demonstrate that the trained ngram representations are useful in many aspects such as finding antonyms and collocations. Besides, a novel approach of building co-occurrence matrix is proposed to alleviate the hardware burdens brought by ngrams.
%R 10.18653/v1/D17-1023
%U https://aclanthology.org/D17-1023
%U https://doi.org/10.18653/v1/D17-1023
%P 244-253