def findRecontructMatchingRules(self, nodeId):
"""
Use modified CKY to just build rules for node.
"""
tokens = self.tree.node(nodeId)
assert len(tokens) > 0
if len(tokens) == 1:
return []
nodeTag = self.getTagOfNode(nodeId)
rc = Reconstructor(self.ruletable, self.model,
self.sense, tokens, nodeTag)
rules = rc.parse()
if rules:
self.recordDependentSitesForNode(nodeId,[-t for t in tokens if t < 0])
return rules
def translateNBestOLD(self,data_tree,data_dep):
"""
Translate and return a N-best list
@type data_tag: string
@type data_dep: string
@rtype: list of GentileHypothesis
"""
# first, we need get the tree of input
self.model.cacheMode = False
setting.load(["nbest", "head_phrases_limit"])
tree = SenseTree(data_tree,data_dep)
tree.rebuildTopNode()
tree.appendXToTree()
tree.upMergeAllConjNodes()
tree.rebuildCommaNodes()
tree.convertTags()
tree.separateContiniousNonTerminals()
# tree.mergeContinuousNTs()
fetcher = self.prepareRulesForTranslation(tree)
# build lexical hypothesis stack
# { id->[lexical hyp,] }
# stack_lex = self.buildLexicalStack(fetcher)
# { id->[lexical hyp,] }
hypStacks = {}
# for each fragment ( head node is not leaf ) at bottom-up style
# use corresponding rules and basic hypothesis(lex or normal) to build normal hyp for this fragment
tree.buildLevelMap()
cur_level = tree.getMaxLevel()
# A dirty trick: save current sense tree to cross-module global variable.
__builtin__.currentSenseTree = tree
# start pruning
self.model.cacheMode = True
while cur_level > 0:
# [head id,]
nodes_cur_level = tree.getNodesByLevel(cur_level)
if cur_level == 1:
self.model.smode = True
else:
self.model.smode = False
for node in nodes_cur_level:
if node not in fetcher.joints:
# only prune for joint nodes
continue
# get rules
rules, sitesInvolved = fetcher.mapJointRules[node]
# okay available could in random order
# we dont need sort it
if not rules:
# No rules found, force to use CYK.
rc = Reconstructor(self.ruletable, self.model,
tree, hypStacks, node)
hyps = rc.parse()
else:
# Rules found then cube prunning.
# sort rules
rules = self.model.sortRules(rules)
# now run the cube pruning and get normal hypothesises for current node
hyps = separately_prune(self.model, node, rules, sitesInvolved, hypStacks)
hypStacks[node] = hyps
self.model.clearCache()
# end of current node
cur_level -= 1
rootNode = tree.getRootNode()
if rootNode not in hypStacks or len(hypStacks[rootNode])==0:
# failed
print "[GentileDecoder]","Translation Failed!!!"
return []
# end building normal hypothesis stack
# hypStacks[rootNode][0].trace()
return hypStacks[rootNode][:setting.nbest]