Research Repository

CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model

Mai, Florian and Galke, Lukas and Scherp, Ansgar (2019) CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model. In: ICLR 2019 : International Conference for Learning Representations, 2019-04-30 - ?, New Orleans. (Unpublished)

[img]
Preview
Text
1902.06423v1.pdf - Accepted Version

Download (339kB) | Preview

Abstract

Continuous Bag of Words (CBOW) is a powerful text embedding method. Due to its strong capabilities to encode word content, CBOW embeddings perform well on a wide range of downstream tasks while being efficient to compute. However, CBOW is not capable of capturing the word order. The reason is that the computation of CBOW's word embeddings is commutative, i.e., embeddings of XYZ and ZYX are the same. In order to address this shortcoming, we propose a learning algorithm for the Continuous Matrix Space Model, which we call Continual Multiplication of Words (CMOW). Our algorithm is an adaptation of word2vec, so that it can be trained on large quantities of unlabeled text. We empirically show that CMOW better captures linguistic properties, but it is inferior to CBOW in memorizing word content. Motivated by these findings, we propose a hybrid model that combines the strengths of CBOW and CMOW. Our results show that the hybrid CBOW-CMOW-model retains CBOW's strong ability to memorize word content while at the same time substantially improving its ability to encode other linguistic information by 8%. As a result, the hybrid also performs better on 8 out of 11 supervised downstream tasks with an average improvement of 1.2%

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: In International Conference on Learning Representations 2019 - Notes: Conference paper at ICLR 2019
Uncontrolled Keywords: cs.CL, cs.CL, cs.LG
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 31 Jul 2019 11:58
Last Modified: 31 Jul 2019 12:15
URI: http://repository.essex.ac.uk/id/eprint/24365

Actions (login required)

View Item View Item