2017 Fiscal Year Annual Research Report
A Study on Social Context Summarization
| Project/Area Number |
15K16048
|
|---|
| Research Institution | Japan Advanced Institute of Science and Technology |
|---|
Principal Investigator |
NGUYEN MinhLe 北陸先端科学技術大学院大学, 先端科学技術研究科, 准教授 (30509401)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Keywords | Sentence extraction / Social context / Deep Learning / Sentence compression / LSTM / Co-factorization |
|---|
| Outline of Annual Research Achievements |
We successfully showed that the support of social context (user-generated content such as comments or tweets and third-party sources can be helpful for extracting high-quality summarizes. The models perform on the three data sets showed promising results in terms of ROUGUE-scores. We also propose an Integer Linear Programming method which utilizing the constraints formulating from social context information. The results showed that our model can improve ROUGE-score compared to the state of the art models on social context summarization. On the other hand, we perform an unsupervised method using matrix co-factorization approach for social context summarization. The model captures the mutual information between sentences and comments by assuming they share hidden topics which achieves promising performance. We work on sentence compression using deep learning which combined model of enhanced Bidirectional Long Short Term Memory (Bi-LSTM) and well-known classifiers such as CRF and SVM for compressing sentence. Our models are trained and evaluated on public English and Vietnamese data sets, showing their state-of-the-art performance.
In addition to the model, we proposed a deep learning model for working on with tree structured and graph structure. The models can work effectively when dealing with the problem of source code analyzing. The models can be applied for the problem of natural language processing including social context summarization.
|
| Remarks |
The system for sentence compression using deep learning.
|
