From 664c5af745786312725917cd9a44418777868350 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Thu, 14 Sep 2017 16:59:25 +0200
Subject: [PATCH] Revert padding in parser

---
 spacy/syntax/_state.pxd    | 6 ++----
 spacy/syntax/nn_parser.pyx | 6 ------
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/spacy/syntax/_state.pxd b/spacy/syntax/_state.pxd
index 9a08691de..4fb16881a 100644
--- a/spacy/syntax/_state.pxd
+++ b/spacy/syntax/_state.pxd
@@ -119,12 +119,10 @@ cdef cppclass StateC:
             # TODO error =/
             pass
         for i in range(n):
-            # Token vectors should be padded, so that there's a vector for
-            # missing values at the start.
             if ids[i] >= 0:
-                ids[i] += this.offset + 1
+                ids[i] += this.offset
             else:
-                ids[i] = 0
+                ids[i] = -1
 
     int S(int i) nogil const:
         if i >= this._s_i:
diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx
index ad6ed280e..3ea17f2fe 100644
--- a/spacy/syntax/nn_parser.pyx
+++ b/spacy/syntax/nn_parser.pyx
@@ -394,7 +394,6 @@ cdef class Parser:
         tokvecs = self.model[0].ops.flatten(tokvecses)
         if USE_FINE_TUNE:
             tokvecs = self.model[0].ops.flatten(self.model[0]((docs, tokvecses)))
-        tokvecs = self._pad_tokvecs(tokvecs)
         nr_state = len(docs)
         nr_class = self.moves.n_moves
         nr_dim = tokvecs.shape[1]
@@ -454,7 +453,6 @@ cdef class Parser:
         tokvecs = self.model[0].ops.flatten(tokvecses)
         if USE_FINE_TUNE:
             tokvecs = self.model[0].ops.flatten(self.model[0]((docs, tokvecses)))
-        tokvecs = self._pad_tokvecs(tokvecs)
         cuda_stream = get_cuda_stream()
         state2vec, vec2scores = self.get_batch_model(len(docs), tokvecs,
                                                      cuda_stream, 0.0)
@@ -527,7 +525,6 @@ cdef class Parser:
         if losses is not None and self.name not in losses:
             losses[self.name] = 0.
         docs, tokvec_lists = docs_tokvecs
-        tokvecs = self.model[0].ops.flatten(tokvec_lists)
         if isinstance(docs, Doc) and isinstance(golds, GoldParse):
             docs = [docs]
             golds = [golds]
@@ -535,7 +532,6 @@ cdef class Parser:
             tokvecs, bp_my_tokvecs = self.model[0].begin_update(docs_tokvecs, drop=drop)
             tokvecs = self.model[0].ops.flatten(tokvecs)
 
-        tokvecs = self._pad_tokvecs(tokvecs)
 
         cuda_stream = get_cuda_stream()
 
@@ -586,7 +582,6 @@ cdef class Parser:
                 break
         self._make_updates(d_tokvecs,
             backprops, sgd, cuda_stream)
-        d_tokvecs = self._unpad_tokvecs(d_tokvecs)
         d_tokvecs = self.model[0].ops.unflatten(d_tokvecs, [len(d) for d in docs])
         if USE_FINE_TUNE:
             d_tokvecs = bp_my_tokvecs(d_tokvecs, sgd=sgd)
@@ -643,7 +638,6 @@ cdef class Parser:
         d_tokvecs = self.model[0].ops.allocate(tokvecs.shape)
         self._make_updates(d_tokvecs, backprop_lower, sgd, cuda_stream)
         d_tokvecs = self.model[0].ops.unflatten(d_tokvecs, lengths)
-        d_tokvecs = self._unpad_tokvecs(d_tokvecs)
         if USE_FINE_TUNE:
             d_tokvecs = bp_my_tokvecs(d_tokvecs, sgd=sgd)
         return d_tokvecs