diff options
| author | aarne <unknown> | 2005-11-01 08:20:09 +0000 |
|---|---|---|
| committer | aarne <unknown> | 2005-11-01 08:20:09 +0000 |
| commit | 27c65e985d1a0c23978239bd52342c766964b98b (patch) | |
| tree | 66071f0b6ab585bf9941ff9fd819c684b838c1e8 | |
| parent | a48236172fc24f32792d56675b0ef682d6119348 (diff) | |
doc of prob
| -rw-r--r-- | doc/gf-history.html | 13 | ||||
| -rw-r--r-- | examples/TWA.cf | 1 | ||||
| -rw-r--r-- | src/GF/Probabilistic/Probabilistic.hs | 6 |
3 files changed, 17 insertions, 3 deletions
diff --git a/doc/gf-history.html b/doc/gf-history.html index 193b18a50..5a50baa46 100644 --- a/doc/gf-history.html +++ b/doc/gf-history.html @@ -12,11 +12,24 @@ Changes in functionality since May 17, 2005, release of GF Version 2.2 </center> +1/11 (AR) Yet another method for adding probabilities: append +<tt> --# prob Double</tt> to the end of a line defining a function. +This can be (1) a <tt>.cf</tt> rule (2) a <tt>fun</tt> rule, or +(3) a <tt>lin</tt> rule. The probability is attached to the +first identifier on the line. + +<p> + 31/10 (AR) Probabilistic grammars. Probabilities can be used to weight random generation (<tt>gr -prob</tt>) and to rank parse results (<tt>p -prob</tt>). They are read from a separate file (flag <tt>i -probs=File</tt>, format <tt>--# prob Fun Double</tt>) or from the top-level grammar file itself (option <tt>i -prob</tt>). +<br> +As a by-product, the probabilistic random generation algorithm is +available for any context-free abstract syntax. Use the flag +<tt>gr -cf<&tt>. This algorithm is much more efficient than the +old (more general) one. <p> diff --git a/examples/TWA.cf b/examples/TWA.cf index 56b14dd2c..32ae7b73f 100644 --- a/examples/TWA.cf +++ b/examples/TWA.cf @@ -1,4 +1,5 @@ -- example of probabilistic grammar from Jurafsky & Martin p. 449 +-- AR 1/11/2005 PredVP. S ::= NP VP ; --# prob 0.80 PredAux. S ::= Aux NP VP ; --# prob 0.15 diff --git a/src/GF/Probabilistic/Probabilistic.hs b/src/GF/Probabilistic/Probabilistic.hs index 1126776c8..5b5c6b2af 100644 --- a/src/GF/Probabilistic/Probabilistic.hs +++ b/src/GF/Probabilistic/Probabilistic.hs @@ -5,9 +5,9 @@ -- Stability : (stable) -- Portability : (portable) -- --- > CVS $Date: 2005/11/01 09:10:54 $ +-- > CVS $Date: 2005/11/01 09:20:09 $ -- > CVS $Author: aarne $ --- > CVS $Revision: 1.4 $ +-- > CVS $Revision: 1.5 $ -- -- Probabilistic abstract syntax. AR 30\/10\/2005 -- @@ -83,7 +83,7 @@ pProb s = case words s of "--#":"prob":f:p:_ | isDouble p -> [(zIdent f, read p)] f:ps@(g:rest) -> case span (/= "--#") ps of (_,_:"prob":p:_) | isDouble p -> [(zIdent f', readD p)] where - f' = if f=="fun" then ident g else ident f + f' = if elem f ["fun","lin","data"] then ident g else ident f _ -> [] _ -> [] where |