projects:swe:start
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
projects:swe:start [2015/05/29 15:07] – hj | projects:swe:start [2015/09/22 01:20] (current) – hj | ||
---|---|---|---|
Line 3: | Line 3: | ||
===== Semantic Word Embedding ===== | ===== Semantic Word Embedding ===== | ||
- | {{: | + | {{: |
\\ | \\ | ||
- | In this project, we propose a general framework | + | In this project, we propose a general framework to incorporate semantic knowledge |
- | to incorporate semantic knowledge | + | into the popular data-driven learning process of word embeddings to improve the |
- | into the popular data-driven learning process | + | quality of them. Under this framework, we represent semantic knowledge as many |
- | of word embeddings to improve the | + | **ordinal ranking inequalities** and formulate the learning of semantic word embeddings |
- | quality of them. Under this framework, | + | (SWE) as a constrained optimization problem, where the data-derived objective |
- | we represent semantic knowledge as many | + | function is optimized subject to all ordinal knowledge inequality constraints |
- | ordinal ranking inequalities and formulate | + | extracted from available knowledge resources such as Thesaurus and Word-Net. We have demonstrated that this constrained optimization problem can be efficiently |
- | the learning of semantic word embeddings | + | solved by the stochastic gradient descent (SGD) algorithm, even for a large |
- | (SWE) as a constrained optimization | + | |
- | problem, where the data-derived objective | + | |
- | function is optimized subject to all | + | |
- | ordinal knowledge inequality constraints | + | |
- | extracted from available knowledge resources | + | |
- | such as Thesaurus and Word- | + | |
- | Net. We have demonstrated that this constrained | + | |
- | optimization problem can be efficiently | + | |
- | solved by the stochastic gradient | + | |
- | descent (SGD) algorithm, even for a large | + | |
number of inequality constraints. | number of inequality constraints. | ||
- | \\ | + | |
+ | **Project website: | ||
+ | |||
+ | * Code and resource download at [[http:// | ||
+ | |||
**Reference: | **Reference: | ||
- | \\ | + | |
- | [1] //Shiliang Zhang and Hui Jiang//, "Hybrid Orthogonal Projection and Estimation | + | |
+ | [1] //Quan Liu, Hui Jiang, Si Wei, Zhen-Hua Ling and Yu Hu//, "Learning SemanticWord Embeddings based on Ordinal Knowledge Constraints," |
projects/swe/start.1432912034.txt.gz · Last modified: 2015/05/29 15:07 by hj