def tag(tagged_string):
""" Takes a PNP-tagged sentence and returns a tagged sentence with the added relation tags.
Tokens in the input string must contain WORD, POS, CHUNK and PNP tags.
Example relation tags: NP-SBJ-1, VP-1, NP-OBJ-1, NP-SBJ-2, ADJP-CLR, ... (see tags.py)
Note 1: on rare occasions words can be tagged with multiple relations (e.g. NP-OBJ-1*NP-OBJ-3).
Note 2: the separator for multiple relation can be "*" OR ";".
"""
s = _split(tagged_string)
verbs, commas, chunks, heads, indices, instance_candidates, VP_chunks = _step1(
s)
distance, comma_map, verb_map = _step2(verbs, commas, chunks, len(s))
tags = []
V = [] # Verb indices collected from _instance().
I = [] # Instance index per tag.
for i in instance_candidates:
instances, verb_indices = _instances(i, distance, verbs, verb_map,
comma_map, heads, indices[i], s)
instances = [x.replace('/', '*') for x in instances]
tags.extend(instances)
V.extend(verb_indices)
I.extend([i] * len(instances))
# The client.batch() function in the client module takes care of managing server clients,
# we simply pass it all the tagging jobs and a definition of the client we need.
tags = client.batch(tags,
client=(client.Timbl, HOST, PORT, config.RELATION,
config.log),
retries=1)
# Getting tags for complete chunks:
chunk_dict = {}
for i, tag in enumerate(tags):
ch = chunks[I[i]]
vp = str(VP_chunks[V[i]])
if tag != '-':
if ch in chunk_dict.keys():
new_tag = '-'.join([tag, vp])
# Do not append a tag referencing to the same verb twice.
# Taking the first occurence:
new_tag_vp = new_tag.split('-')[-1]
linked_vps = [
x.split('-')[-1] for x in chunk_dict[ch].split('*')
]
if new_tag_vp not in linked_vps:
chunk_dict[ch] += '*' + new_tag
else:
chunk_dict[ch] = '-'.join([tag, vp])
# Collect NP-SBJ, NP-OBJ etc. relations and add the VP relations.
# Place the relation tags in the sentence.
relations = []
for i, chunk in enumerate(chunks):
if chunk in chunk_dict:
relations.append(chunk_dict[chunk])
elif VP_chunks[i]:
relations.append('VP-%d' % (VP_chunks[i]))
else:
relations.append('O')
for i in range(len(s)):
s[i][4] = relations[i]
return _join(s)
def tag(tagged_string):
""" Takes a PNP-tagged sentence and returns a tagged sentence with the added relation tags.
Tokens in the input string must contain WORD, POS, CHUNK and PNP tags.
Example relation tags: NP-SBJ-1, VP-1, NP-OBJ-1, NP-SBJ-2, ADJP-CLR, ... (see tags.py)
Note 1: on rare occasions words can be tagged with multiple relations (e.g. NP-OBJ-1*NP-OBJ-3).
Note 2: the separator for multiple relation can be "*" OR ";".
"""
s = _split(tagged_string)
verbs, commas, chunks, heads, indices, instance_candidates, VP_chunks = _step1(s)
distance, comma_map, verb_map = _step2(verbs, commas, chunks, len(s))
tags = []
V = [] # Verb indices collected from _instance().
I = [] # Instance index per tag.
for i in instance_candidates:
instances, verb_indices = _instances(i, distance, verbs, verb_map, comma_map, heads, indices[i], s)
instances = [x.replace('/','*') for x in instances]
tags.extend(instances)
V.extend(verb_indices)
I.extend([i] * len(instances))
# The client.batch() function in the client module takes care of managing server clients,
# we simply pass it all the tagging jobs and a definition of the client we need.
tags = client.batch(tags, client=(client.Timbl, HOST, PORT, config.RELATION, config.log), retries=1)
# Getting tags for complete chunks:
chunk_dict = {}
for i, tag in enumerate(tags):
ch = chunks[I[i]]
vp = str(VP_chunks[V[i]])
if tag != '-':
if ch in chunk_dict.keys():
new_tag = '-'.join([tag, vp])
# Do not append a tag referencing to the same verb twice.
# Taking the first occurence:
new_tag_vp = new_tag.split('-')[-1]
linked_vps = [x.split('-')[-1] for x in chunk_dict[ch].split('*')]
if new_tag_vp not in linked_vps:
chunk_dict[ch] += '*' + new_tag
else:
chunk_dict[ch] = '-'.join([tag, vp])
# Collect NP-SBJ, NP-OBJ etc. relations and add the VP relations.
# Place the relation tags in the sentence.
relations = []
for i, chunk in enumerate(chunks):
if chunk in chunk_dict:
relations.append(chunk_dict[chunk])
elif VP_chunks[i]:
relations.append('VP-%d' % (VP_chunks[i]))
else:
relations.append('O')
for i in range(len(s)):
s[i][4] = relations[i]
return _join(s)
def _chunk(string):
""" Takes a tokenized and escaped string where sentences are separated by a new line.
Returns a string where words have been tagged with their part-of-speech and chunk tags.
Common part-of-speech tags include NN (noun), VB (verb), JJ (adjective), PP (preposition).
Common chunk tags include NP (noun phrase), VP (verb phrase), ...
- input: ['Draw a red car .']
- output: Draw/VB/I-VP a/DT/I-NP red/JJ/I-NP car/NN/I-NP ././O
"""
sentences = filter(lambda x: len(x)>0, string.splitlines())
host = HOSTS[CHUNK]
port = PORTS[CHUNK]
# Send the sentences to the TiMBL server.
# The batch() function in the client module takes care of managing server clients,
# we simply pass it all the tagging jobs and a definition of the client we need.
return '\n'.join(client.batch(sentences, client=(client.Mbt, host, port, CHUNK, config.log), retries=1))
def _chunk(string):
""" Takes a tokenized and escaped string where sentences are separated by a new line.
Returns a string where words have been tagged with their part-of-speech and chunk tags.
Common part-of-speech tags include NN (noun), VB (verb), JJ (adjective), PP (preposition).
Common chunk tags include NP (noun phrase), VP (verb phrase), ...
- input: ['Draw a red car .']
- output: Draw/VB/I-VP a/DT/I-NP red/JJ/I-NP car/NN/I-NP ././O
"""
sentences = filter(lambda x: len(x) > 0, string.splitlines())
host = HOSTS[CHUNK]
port = PORTS[CHUNK]
# Send the sentences to the TiMBL server.
# The batch() function in the client module takes care of managing server clients,
# we simply pass it all the tagging jobs and a definition of the client we need.
return '\n'.join(
client.batch(sentences,
client=(client.Mbt, host, port, CHUNK, config.log),
retries=1))
