earticle

논문검색

Incorporating Topic Priors into Distributed Word Representations

초록

영어

Representing words as continuous vectors enables the quantification of semantic relationships of words by vector operations, thereby has attracted much attention recently. This paper proposes an approach to combine continuous word representation and topic modeling, by encoding words based on their topic distributions in the hierarchical softmax, so as to introduce the prior semantic relevance information into the neural networks. The word vectors generated by our model are evaluated with respect to word relevance and the document relevance. Experimental results show that our approach is promising for further improving the quality of word vectors.

목차

Abstract
 1. Introduction
 2. Related Work
 3. Approach
  3.1. Word Encoding via Topic Distributions 
  3.2. Topic Modeling
 4. Experiments
  4.1. Experimental Setting
  4.2. Evaluation Tasks
  4.3. Results and Discussion
 5. Conclusions
 Acknowledgments
 References

저자정보

  • Xin Zhang School of Computer Science and Technology, Harbin Institute of Technology, 92 West Da Zhi St, Harbin, China
  • Bingquan Liu School of Computer Science and Technology, Harbin Institute of Technology, 92 West Da Zhi St, Harbin, China
  • Baoxun Wang Application and Service Group, Microsoft, Beijing, China
  • Xiaolong Wang School of Computer Science and Technology, Harbin Institute of Technology, 92 West Da Zhi St, Harbin, China
  • Deyuan Zhang School of Computer, Shenyang Aerospace University, Shenyang, China

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.