원문정보
초록
영어
Value tracking aims to capture the changes of attribute values along with the evolution of topic. Existing researches on value tracking only extracted the attribute values chronologically, and took no use of the context information to verify the correctness of the values. This paper proposes a context-based value tracking method. First, extract the candidate attribute values according to the patterns generated by the regular expressions; Second, recognize the temporal expressions in the source sentences of the candidate values based on conditional random fields; Finally, identify the real attribute values according to the temporal features and location features in the context. Experiments on TREC 2013 Knowledge Base Acceleration (KBA) stream corpus and human-build Chinese corpus demonstrate that the proposed method can track the changes of the attribute values effectively.
목차
1. Introduction
2. Related Work
3. Analysis of the Importance of Context
4. Methodology
4.1. Candidate Attribute Value Extraction
4.2. Temporal Expression Recognition
4.3. Value Tracking
5. Experiments
5.1. Datasets
5.2. Evaluation Metrics
5.3. Results
5.4. Display the Changes of Attribute Value
6. Conclusion
Acknowledgments
References