Difference between revisions of "Bo Pang Sujith Ravi 2012 Revisiting the Predictability of Language: Response Completion in Social Media"
From Cohen Courses
Jump to navigationJump to search| Line 9: | Line 9: | ||
This paper propose a method for automatic response completion by considering mainly two factors: | This paper propose a method for automatic response completion by considering mainly two factors: | ||
| + | |||
| + | |||
1) The language used in responses (By using Language Model[LM](bigram model & trigram model(both back-off to unigram))) | 1) The language used in responses (By using Language Model[LM](bigram model & trigram model(both back-off to unigram))) | ||
| + | |||
| + | |||
2) The specific context provided by the original message. | 2) The specific context provided by the original message. | ||
| + | |||
| + | |||
[TM]Besides using methods In Ritter et. al 2010, Data-Driven Response Generation in Social Media, which is to use a translation model to do alignment between stimulus(source) and the response(target). [IBM-Model1] | [TM]Besides using methods In Ritter et. al 2010, Data-Driven Response Generation in Social Media, which is to use a translation model to do alignment between stimulus(source) and the response(target). [IBM-Model1] | ||
Revision as of 20:16, 26 September 2012
Contents
Citation
Revisiting the Predictability of Language: Response Completion in Social Media, Bo Pang Sujith Ravi, EMNLP 2012
Online version
An online pdf version is here[1]
Summary
This paper propose a method for automatic response completion by considering mainly two factors:
1) The language used in responses (By using Language Model[LM](bigram model & trigram model(both back-off to unigram)))
2) The specific context provided by the original message.
[TM]Besides using methods In Ritter et. al 2010, Data-Driven Response Generation in Social Media, which is to use a translation model to do alignment between stimulus(source) and the response(target). [IBM-Model1]
