class MaltParser(DependencyParserWrapper):
# currently this can only be run from the malt parser directory
# TODO: make more general/easy to run
def __init__(self, version = "maltparser-1.9.2", model = "engmalt.linear-1.7.mco"):
super().__init__()
root = os.getcwd()
version_path = os.path.join(root, "schemata", "parse", "maltparser", version )
model_path =os.path.join(root, "schemata", "parse", "maltparser", model )
self.base = MP(version_path, model_path)
def get_spans(self, sent):
dparse = self.base.parse_one(sent.split())
heads = [node['head'] for _, node in sorted(dparse.nodes.items())][1:]
tree = DependencyParserWrapper.head_to_tree(heads)
non_singletons = DependencyParserWrapper.compute_spans(tree)
singletons = [(n, n+1) for n in range(len(heads))]
return set(non_singletons) | set(singletons)
sublist1 = path1[j:]
#print("sublist1",sublist1)
if j< len(path2)-1:
j=j+1
sublist2 = path2[j:]
#print("sublist2",sublist2)
sublist2.reverse()
#print("sublist2",sublist2)
shortestpath = sublist2 + sublist1
return shortestpath
dparser = MaltParser('../data/grammars/maltparser-1.8.1/', 'engmalt.linear-1.7.mco')
pt = dparser.parse_one('I shot an elephant in my pajamas .'.split()).tree()
# print(pt)
# print(pt)
# print(shortestPath(pt,'I','pajamas'))
# print(shortestPath(pt,'I','pajamas'))
# print(shortestPath(pt,'elephant','pajamas'))
# print(shortestPath(pt,'I','elephant'))
# parsing many sentences
tagged_sents= [
"The other day I went to the beach.".split(),
sublist1 = path1[j:]
#print("sublist1",sublist1)
if j < len(path2) - 1:
j = j + 1
sublist2 = path2[j:]
#print("sublist2",sublist2)
sublist2.reverse()
#print("sublist2",sublist2)
shortestpath = sublist2 + sublist1
return shortestpath
dparser = MaltParser('../data/grammars/maltparser-1.8.1/',
'engmalt.linear-1.7.mco')
pt = dparser.parse_one('I shot an elephant in my pajamas .'.split()).tree()
# print(pt)
# print(pt)
# print(shortestPath(pt,'I','pajamas'))
# print(shortestPath(pt,'I','pajamas'))
# print(shortestPath(pt,'elephant','pajamas'))
# print(shortestPath(pt,'I','elephant'))
# parsing many sentences
tagged_sents = [
"The other day I went to the beach.".split(),
"It was a hot day so I swimmed in the water.".split()
]
import sys
from nltk.parse.malt import MaltParser
PATH_TO_MALTPARSER = "maltparser-1.9.2"
PATH_TO_MODEL = "kaist-conll.mco"
def print_usage():
print("usage: $ python3 parser.py <input text>")
if __name__ == '__main__':
argv = sys.argv[1:]
argc = len(sys.argv)
if (argc != 2):
print_usage()
sys.exit()
user_input = argv[0]
tokens = user_input.split()
mp = MaltParser(PATH_TO_MALTPARSER, PATH_TO_MODEL)
graph = mp.parse_one(tokens).tree()
print(graph)
