Difference between revisions of "Tianyi Luo 2016-01-04"

From cslt Wiki
Jump to: navigation, search
Line 6: Line 6:
 
=== Work done in this week ===
 
=== Work done in this week ===
 
* Finish installing the Moses and conduct the couplet generation experiments with SMT method. [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/da/2016-01-04_Tianyi_Luo%27s_couplet_generation.pdf Samples]]
 
* Finish installing the Moses and conduct the couplet generation experiments with SMT method. [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/da/2016-01-04_Tianyi_Luo%27s_couplet_generation.pdf Samples]]
 +
The tutoial about how to install Moses and conduct the training and testing is as following: [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/7f/Moses%E5%AE%89%E8%A3%85%E8%AE%AD%E7%BB%83%E5%85%A8%E8%BF%87%E7%A8%8B.pdf Tutoial]].
 +
 
=== Plan to do next week ===
 
=== Plan to do next week ===
 
* To finish the work about the SMT method implementation of the poem generation and to extract the SMT features to enhance the function of poem generation and songci generation.
 
* To finish the work about the SMT method implementation of the poem generation and to extract the SMT features to enhance the function of poem generation and songci generation.

Revision as of 08:37, 4 January 2016

Plan to do next week

  • To finish the work about the SMT method implementation of the poem generation.
  • To tackle the problem of attention-based programe.
  • To implement the reading comprehension qa system.
  • To extract the SMT features to enhance the function of poem generation and songci generation.

Work done in this week

  • Finish installing the Moses and conduct the couplet generation experiments with SMT method. [Samples]

The tutoial about how to install Moses and conduct the training and testing is as following: [Tutoial].

Plan to do next week

  • To finish the work about the SMT method implementation of the poem generation and to extract the SMT features to enhance the function of poem generation and songci generation.
  • To implement the reading comprehension qa system.

Interested papers

  • Cascading Bandits: Learning to Rank in the Cascade Model(ICML 2015) [pdf]