Adaptive compression of word embeddings

Yeachan Kim, Kang Min Kim, Sang Keun Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)


Distributed representations of words have been an indispensable component for natural language processing (NLP) tasks. However, the large memory footprint of word embeddings makes it challenging to deploy NLP models to memory-constrained devices (e.g., self-driving cars, mobile devices). In this paper, we propose a novel method to adaptively compress word embeddings. We fundamentally follow a code-book approach that represents words as discrete codes such as (8, 5, 2, 4). However, unlike prior works that assign the same length of codes to all words, we adaptively assign different lengths of codes to each word by learning downstream tasks. The proposed method works in two steps. First, each word directly learns to select its code length in an end-to-end manner by applying the Gumbel-softmax tricks. After selecting the code length, each word learns discrete codes through a neural network with a binary constraint. To showcase the general applicability of the proposed method, we evaluate the performance on four different downstream tasks. Comprehensive evaluation results clearly show that our method is effective and makes the highly compressed word embeddings without hurting the task accuracy. Moreover, we show that our model assigns word to each code-book by considering the significance of tasks.

Original languageEnglish
Title of host publicationACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Number of pages10
ISBN (Electronic)9781952148255
Publication statusPublished - 2020
Event58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Virtual, Online, United States
Duration: 2020 Jul 52020 Jul 10

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X


Conference58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Country/TerritoryUnited States
CityVirtual, Online

Bibliographical note

Funding Information:
This work was supported by Institute of Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2019-0-00079 , Artificial Intelligence Graduate School Program(Korea University)), and the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2018R1A2A1A05078380).

Publisher Copyright:
© 2020 Association for Computational Linguistics

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics


Dive into the research topics of 'Adaptive compression of word embeddings'. Together they form a unique fingerprint.

Cite this