Skip to content

Commit c75a28a

Browse files
authored
Update README.md
add figure in README.md
1 parent 1205ec4 commit c75a28a

File tree

1 file changed

+2
-0
lines changed

1 file changed

+2
-0
lines changed

README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,8 @@ Learning Discrete Sentence Representations via Construction & Decomposition [[Sp
77
## Abstract
88
In this paper, we address the problem of learning low-dimensional, discrete representations of real-valued vectors. We propose a new algorithm called similarity matrix construction and decomposition (C\&D). In the preparation phase, we constructively generate a set of consistent, unbiased and comprehensive anchor vectors, and obtain their low-dimensional forms with PCA. The C\&D algorithm learns the discrete representations of vectors in batches. For a batch of input vectors, we first construct a similarity matrix between them and the anchor vectors, and then learn their discrete representations from the similarity matrix decomposition, where the low-dimensional forms of the anchor vectors are regarded as a fixed factor of the similarity matrix. The matrix decomposition is a mixed-integer optimization problem. We obtain the optimal solution for each bit with mathematical derivation, and then use the discrete coordinate descent method to solve it. The C\&D algorithm does not learn directly discrete representations from the input vectors, which distinguishes it from other discrete learning algorithms. We evaluate the C\&D algorithm on sentence embedding compression tasks. Extensively experimental results reveal the C\&D algorithm outperforms the latest 4 methods and reaches state-of-the-art. Detailed analysis and ablation study further validate the rationality of the C\&D algorithm.
99

10+
## Algorithm
11+
![Algorithm Overview](https://github.com/songs18/PictureSet/blob/main/CD.svg)
1012
## Usage
1113
The experimental environment of C&D algorithm is consistent with [repository](https://github.com/Linear95/BinarySentEmb) This means that using this repository requires 3 simple steps:
1214
1. Set up the experimental environment according to the [repository](https://github.com/Linear95/BinarySentEmb) instructions.

0 commit comments

Comments
 (0)