[Ligncse256] [LIGN 256] J&M question/comment

[Roger Levy]

Ben Cipollini wrote:
> Hi Roger,
>  
> I had a question/comment about the Jurafsky & Martin book.  In chapter 
> 6, p.188, the backward probability (beta) is explained.  I believe that 
> the "i" in equation 6.28 is very different rom the "i" dummy-variable in 
> eqations 6.29 and 6.30.  If that's the case, then that could be made 
> much clearer in the book.  I thought the "i" in 6.29 and 6.30 was the 
> same "given" value used for equation 6.28 (the sentence before 6.28 says 
> "given we are in state i ..."
>  
> If i'm missing something, please let me know.  Otherwise, it would be 
> great if you could forward a comment to the authors...

Hi Ben,

No, I believe that the "i" variable is the same in all cases: it indexes 
  the state of interest. 6.28 is a definition of the backward 
probability, and 6.29 & 6.30 say how to set it.  Does that make sense?

I think it might be a bit clearer if the sentence before 6.28 began with:

   The backward probability \beta_t(i) ...

Roger



-- 

Roger Levy                      Email: rlevy at ucsd.edu
Assistant Professor             Phone: 858-534-7219
Department of Linguistics       Fax:   858-534-4789
UC San Diego                    Web:   http://ling.ucsd.edu/~rlevy