Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update Summarization Based on Co-Ranking with Constraints, Wiaojun Wan, COLING’12 #30

Open
AkihikoWatanabe opened this issue Dec 28, 2017 · 1 comment

Comments

@AkihikoWatanabe
Copy link
Owner

https://pdfs.semanticscholar.org/21c2/30d55c44f75e2c7cf4d57f1bf3df513bdfef.pdf

@AkihikoWatanabe
Copy link
Owner Author

・PageRankの枠組みを拡張してold datasetとnew dataset内のsentenceをco-ranking
・co-rankingするときは,update scoreとconsistency scoreというものを求め相互作用させる.
・update scoreが高いsentenceは同じdataset内では正の関係,異なるdataset内では負の関係を持つ.
・consistency scoreが高いsentenceは同じdataset内では正の関係,異なるdataset内では正の関係を持つ.
・負の関係はdissimilarity matrixを用いて表現する.
・あとはupdate scoreとconsistency scoreを相互作用させながらPageRankでスコアを求める.デコーディングはupdate scoreをgreedyに.
・update scoreとconsistency scoreの和は定数と定義,この論文では定数をsentenceのinformative scoreとしている.これがタイトルにある制約.informative scoreはAffinity GraphにPageRankを適用して求める.
・制約が入ることで,consistency scoreが低いとupdate scoreは高くなるような効果が生まれる.逆もしかり.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant