explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 08:12:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Start adding parse features to sense_tagger

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-06 08:43:24 +02:00
parent cb628ba352
commit b61b495024
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
spacy/sense_tagger.pyx
View File

@ -56,17 +56,32 @@ cdef enum:
N2c N2c
N2c6 N2c6
N2c4 N2c4
Hw
Hp
Hc
Hc6
Hc4
N3W N3W
P3W P3W
P1s P1s
P2s P2s
CONTEXT_SIZE CONTEXT_SIZE
unigrams = ( unigrams = (
(Hw,),
(Hp,),
(Hw, Hp),
(Hc, Hp),
(Hc6, Hp),
(Hc4, Hp),
(Hc,),
(P2W,), (P2W,),
(P2p,), (P2p,),
(P2W, P2p), (P2W, P2p),
@ -189,6 +204,7 @@ cdef int fill_context(atom_t* ctxt, const TokenC* token) except -1:
fill_token(&ctxt[N1W], token + 1) fill_token(&ctxt[N1W], token + 1)
fill_token(&ctxt[N2W], token + 2) fill_token(&ctxt[N2W], token + 2)
fill_token(&ctxt[Hw], token + token.head)
ctxt[P1s] = (token - 1).sense ctxt[P1s] = (token - 1).sense
ctxt[P2s] = (token - 2).sense ctxt[P2s] = (token - 2).sense
ctxt[N3W] = (token + 3).lemma ctxt[N3W] = (token + 3).lemma
@ -334,7 +350,7 @@ cdef class SenseTagger:
token.sense = 1 token.sense = 1
return cost return cost
cdef dict _perceptron_update(self, const Feature* feats, int n_feats, int guess, int best): cdef dict _make_update(self, const Feature* feats, int n_feats, int guess, int best):
guess_counts = {} guess_counts = {}
gold_counts = {} gold_counts = {}
if guess != best: if guess != best: