"""
## 47.Functional verb syntax mining[Permalink](https://nlp100.github.io/ja/ch05.html#47-Functionalverbsyntaxmining)
I would like to pay attention only when the verb wo case contains a s-irregular noun. Modify 46 programs to meet the following specifications.
-"Sahen connection noun+Only when the phrase composed of "(particle)" is related to the verb
-The predicate is "Sahen connecting noun"+To+動詞の基本形」とし，文節中に複数の動詞があるときは，最左の動詞To用いる
-If there are multiple particles (phrases) related to the predicate, arrange all the particles in lexicographic order separated by spaces.
-If there are multiple clauses related to the predicate, arrange all the terms with spaces (align with the order of particles).
For example, the following output should be obtained from the sentence "There is also a method called reinforcement learning in which learning is performed based on one's own experience."
Experience based on learning
"""
from collections import defaultdict
from typing import List
def read_file(fpath: str) -> List[List[str]]:
"""Get clear format of parsed sentences.
Args:
fpath (str): File path.
Returns:
List[List[str]]: List of sentences, and each sentence contains a word list.
e.g. result[1]:
['* 0 2D 0/0 -0.764522',
'\u3000\t sign,Blank,*,*,*,*,\u3000,\u3000,\u3000',
'* 1 2D 0/1 -0.764522',
'I\t noun,Pronoun,General,*,*,*,I,Wagamama,Wagamama',
'Is\t particle,Particle,*,*,*,*,Is,C,Wow',
'* 2 -1D 0/2 0.000000',
'Cat\t noun,General,*,*,*,*,Cat,cat,cat',
'so\t auxiliary verb,*,*,*,Special,Continuous form,Is,De,De',
'is there\t auxiliary verb,*,*,*,Five steps, La line Al,Uninflected word,is there,Al,Al',
'。\t sign,Kuten,*,*,*,*,。,。,。']
"""
with open(fpath, mode="rt", encoding="utf-8") as f:
sentences = f.read().split("EOS\n")
return [sent.strip().split("\n") for sent in sentences if sent.strip() != ""]
class Morph:
"""Morph information for each token.
Args:
data (dict): A dictionary contains necessary information.
Attributes:
surface (str):Surface
base (str):Uninflected word (base)
pos (str):Part of speech (base)
pos1 (str):Part of speech subclassification 1 (pos1)
"""
def __init__(self, data):
self.surface = data["surface"]
self.base = data["base"]
self.pos = data["pos"]
self.pos1 = data["pos1"]
def __repr__(self):
return f"Morph({self.surface})"
def __str__(self):
return "surface[{}]\tbase[{}]\tpos[{}]\tpos1[{}]".format(
self.surface, self.base, self.pos, self.pos1
)
class Chunk:
"""Containing information for Clause/phrase.
Args:
data (dict): A dictionary contains necessary information.
Attributes:
chunk_id (str): The number of clause chunk (Phrase number).
morphs List[Morph]: Morph (morpheme) list.
dst (str): The index of dependency target (Contact clause index number).
srcs (List[str]): The index list of dependency source. (Original clause index number).
"""
def __init__(self, chunk_id, dst):
self.id = chunk_id
self.morphs = []
self.dst = dst
self.srcs = []
def __repr__(self):
return "Chunk( id: {}, dst: {}, srcs: {}, morphs: {} )".format(
self.id, self.dst, self.srcs, self.morphs
)
def get_surface(self) -> str:
"""Concatenate morph surfaces in a chink.
Args:
chunk (Chunk): e.g. Chunk( id: 0, dst: 5, srcs: [], morphs: [Morph(I), Morph(Is)]
Return:
e.g. 'I am'
"""
morphs = self.morphs
res = ""
for morph in morphs:
if morph.pos != "symbol":
res += morph.surface
return res
def validate_pos(self, pos: str) -> bool:
"""Return Ture if 'noun' or 'verb' in chunk's morphs. Otherwise, return False."""
morphs = self.morphs
return any([morph.pos == pos for morph in morphs])
def convert_sent_to_chunks(sent: List[str]) -> List[Morph]:
"""Extract word and convert to morph.
Args:
sent (List[str]): A sentence contains a word list.
e.g. sent:
['* 0 1D 0/1 0.000000',
'I\t noun,Pronoun,General,*,*,*,I,Wagamama,Wagamama',
'Is\t particle,Particle,*,*,*,*,Is,C,Wow',
'* 1 -1D 0/2 0.000000',
'Cat\t noun,General,*,*,*,*,Cat,cat,cat',
'so\t auxiliary verb,*,*,*,Special,Continuous form,Is,De,De',
'is there\t auxiliary verb,*,*,*,Five steps, La line Al,Uninflected word,is there,Al,Al',
'。\t sign,Kuten,*,*,*,*,。,。,。']
Parsing format:
e.g. "* 0 1D 0/1 0.000000"
|column|meaning|
| :----: | :----------------------------------------------------------- |
| 1 |The first column is`*`.. Indicates that this is a dependency analysis result.|
| 2 |Phrase number (integer starting from 0)|
| 3 |Contact number +`D` |
| 4 |Head/Function word positions and any number of feature sequences|
| 5 |Engagement score. In general, the larger the value, the easier it is to engage.|
Returns:
List[Chunk]: List of chunks.
"""
chunks = []
chunk = None
srcs = defaultdict(list)
for i, word in enumerate(sent):
if word[0] == "*":
# Add chunk to chunks
if chunk is not None:
chunks.append(chunk)
# eNw Chunk beggin
chunk_id = word.split(" ")[1]
dst = word.split(" ")[2].rstrip("D")
chunk = Chunk(chunk_id, dst)
srcs[dst].append(chunk_id) # Add target->source to mapping list
else: # Add Morch to chunk.morphs
features = word.split(",")
dic = {
"surface": features[0].split("\t")[0],
"base": features[6],
"pos": features[0].split("\t")[1],
"pos1": features[1],
}
chunk.morphs.append(Morph(dic))
if i == len(sent) - 1: # Add the last chunk
chunks.append(chunk)
# Add srcs to each chunk
for chunk in chunks:
chunk.srcs = list(srcs[chunk.id])
return chunks
def validate_chunk(chunk: Chunk, chunks: List[Chunk]) -> bool:
"""Validate chunk contains s-irregular connection nouns(sa_connect_noun)and (particle)(particle).
Args:
chunk (Chunk): Chunk object.
e.g. Chunk( id: 4, dst: 5, srcs: ['3'], morphs: [Morph(thing), Morph(To)] )
Returns:
bool: True or False
"""
sa_hen_flag = False
jyo_shi_flag = False
verb_flag = False
for morph in chunk.morphs:
if morph.pos1 == "Change connection":
sa_hen_flag = True
if morph.pos == "Particle" and morph.surface == "To":
jyo_shi_flag = True
if (not sa_hen_flag) and (not jyo_shi_flag):
return False
for src in chunk.srcs:
src_chunk = chunks[int(src)]
for morph in src_chunk.morphs:
if morph.pos == "verb":
verb_flag = True
return all([sa_hen_flag, jyo_shi_flag, verb_flag])
def get_verb_frame(chunks: List[Chunk]) -> dict:
"""Get edges from sentence chunks.
Terms:
-predicate(predicate)
-Item(argument)
-Case(case)
Notice:
- Chunk.morphs have "sa-hen connection noun" and "o (particle)"
- Chunk.srcs have "verbs"
Args:
chunks (List[Chunk]): A sentence contains many chunks.
e.g. [Chunk( id: 0, dst: 5, srcs: [], morphs: [Morph(I), Morph(Is)] ),
Chunk( id: 1, dst: 2, srcs: [], morphs: [Morph(here), Morph(so)] ),
Chunk( id: 2, dst: 3, srcs: ['1'], morphs: [Morph(start), Morph(hand)] ),
Chunk( id: 3, dst: 4, srcs: ['2'], morphs: [Morph(Human), Morph(That)] ),
Chunk( id: 4, dst: 5, srcs: ['3'], morphs: [Morph(thing), Morph(To)] ),
Chunk( id: 5, dst: -1, srcs: ['0', '4'], morphs: [Morph(You see), Morph(Ta), Morph(。)] )]
Returns:
dict: Predicate frame.
e.g. {'pred': 'talk', 'case': [], 'arg': []}
or {'pred': 'See a laugh', 'case': ['hand'], 'arg': ['見hand']}
or {'pred': 'Have a demonstration', 'case': ['hand', 'To'], 'arg': ['持っhand', '性格To']},
"""
frame = {"pred": None, "case": [], "arg": []}
for chunk in chunks:
# Initialize
sa_hen_surface = None
# Skip if not valid
if not validate_chunk(chunk, chunks):
continue
# Get sa_hen
for morph in chunk.morphs:
if morph.pos1 == "Change connection":
sa_hen_surface = morph.surface
# Get verb
src_verb_chunks = [
morph
for src in chunk.srcs
for morph in chunks[int(src)].morphs
if morph.pos == "verb"
]
# Get predicate
frame["pred"] = sa_hen_surface + "To" + src_verb_chunks[0].base
# Get case
for src in chunk.srcs:
src_chunk = chunks[int(src)]
for morph in src_chunk.morphs:
if morph.pos == "Particle":
frame["case"].append(morph.base)
frame["arg"].append(src_chunk.get_surface())
return frame
def write_to_file(sents: List[dict], path):
"""Write patterns to file.
Args:
sents ([type]): predicate-verb frame
e.g. [{'pred': 'talk', 'case': [], 'arg': []},
{'pred': 'See a laugh', 'case': ['hand'], 'arg': ['見hand']},
{'pred': 'Have a demonstration', 'case': ['hand', 'To'], 'arg': ['持っhand', '性格To']}]
"""
# convert_frame_to_text
lines = []
for frame in sents:
case_text = " ".join(frame["case"])
arg_text = " ".join(frame["arg"])
lines.append((frame["pred"], case_text, arg_text))
# write_to_file
with open(path, "w") as f:
for line in lines:
f.write(f"{line[0]}\t{line[1]}\t{line[2]}\n")
fpath = "neko.txt.cabocha"
sentences = read_file(fpath)
sentences = [convert_sent_to_chunks(sent) for sent in sentences] # ans41
# ans47
pattern_sents = [get_verb_frame(sent) for sent in sentences]
pattern_sents = list(filter(lambda x: x["pred"] is not None, pattern_sents))
write_to_file(pattern_sents, "predicate_verb_frame.txt")
# "predicate_verb_frame.txt":
#talk
#Look at the laughter
#Grief the press
#I wonder if I will listen to my imagination and write it down.
#Controversy
#Misguided greetings
#After reading aloud
#Have a personality
Recommended Posts