2015/11/19 by Martin Andrews, Andrews, Martin
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.1511.06397
10 pages, 0 figures, submitted to ICONIP-2016. Previous experimental results were submitted to ICLR-2016, but the paper has been significantly updated, since a new experimental set-up worked much better
arxiv created 2016/05/16 · arxiv updated 2016/05/17
Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic. However, these vector space representations (created through large-scale text analysis) are typically stored verbatim, since their internal structure is opaque. Using word-analogy tests to monitor the level of detail stored in compressed re-representations of the same vector space, the trade-offs between the reduction in memory usage and expressiveness are investigated. A simple scheme is outlined that can reduce the memory footprint of a state-of-the-art embedding by a factor of 10, with only minimal impact on performance. Then, using the same `bit budget', a binary (approximate) factorisation of the same space is also explored, with the aim of creating an equivalent representation with better interpretability.