"""
42.Anzeige der Phrase der verantwortlichen Person und der verantwortlichen Person
Extrahieren Sie den gesamten Text der ursprünglichen Klausel und den Text der Klausel im durch Tabulatoren getrennten Format. Geben Sie jedoch keine Symbole wie Satzzeichen aus.
"""
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 Symbol,Leer,*,*,*,*,\u3000,\u3000,\u3000',
'* 1 2D 0/1 -0.764522',
'ich\t Substantiv,Gleichbedeutend,Allgemeines,*,*,*,ich,Wagahai,Wagahai',
'Ist\t Assistent,Hilfe,*,*,*,*,Ist,C.,Beeindruckend',
'* 2 -1D 0/2 0.000000',
'Katze\t Substantiv,Allgemeines,*,*,*,*,Katze,Katze,Katze',
'damit\t Hilfsverb,*,*,*,Besondere,Kontinuierlicher Typ,Ist,De,De',
'Gibt es\t Hilfsverb,*,*,*,Fünf Schritte, La Linie Al,Grundform,Gibt es,Al,Al',
'。\t Symbol,Phrase,*,*,*,*,。,。,。']
"""
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):Oberfläche
base (str):Base
pos (str):Teil (Basis)
pos1 (str):Teil Teil Unterklassifizierung 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 (Phrasennummer).
morphs List[Morph]: Morph (Morphem) list.
dst (str): The index of dependency target (Indexnummer der Kontaktklausel).
srcs (List[str]): The index list of dependency source. (Original-Klauselindexnummer).
"""
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 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',
'ich\t Substantiv,Gleichbedeutend,Allgemeines,*,*,*,ich,Wagahai,Wagahai',
'Ist\t Assistent,Hilfe,*,*,*,*,Ist,C.,Beeindruckend',
'* 1 -1D 0/2 0.000000',
'Katze\t Substantiv,Allgemeines,*,*,*,*,Katze,Katze,Katze',
'damit\t Hilfsverb,*,*,*,Besondere,Kontinuierlicher Typ,Ist,De,De',
'Gibt es\t Hilfsverb,*,*,*,Fünf Schritte, La Linie Al,Grundform,Gibt es,Al,Al',
'。\t Symbol,Phrase,*,*,*,*,。,。,。']
Parsing format:
e.g. "* 0 1D 0/1 0.000000"
|Säule|Bedeutung|
| :----: | :----------------------------------------------------------- |
| 1 |Die erste Spalte ist`*`.. Zeigt an, dass es sich um ein Ergebnis der Abhängigkeitsanalyse handelt.|
| 2 |Phrasennummer (Ganzzahl ab 0)|
| 3 |Kontaktnummer +`D` |
| 4 |Hauptadresse/Funktionswortposition und beliebig viele Identitätsspalten|
| 5 |Verlobungspunktzahl. Im Allgemeinen ist es umso einfacher, sich zu engagieren, je größer der Wert ist.|
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 concat_morphs_surface(chunk: Chunk) -> str:
"""Concatenate morph surfaces in a chink.
Args:
chunk (Chunk): e.g. Chunk( id: 0, dst: 5, srcs: [], morphs: [Morph(ich), Morph(Ist)]
Return:
e.g. 'ich bin'
"""
res = ""
for morph in chunk.morphs:
if morph.pos != "Symbol":
res += morph.surface
return res
def concat_chunks_surface(chunks: List[Chunk]):
"""Concatenate surface of dependency source and target between chunks.
Args:
chunks (List[Chunk]): chunks represent a sentences.
e.g. [Chunk( id: 0, dst: 5, srcs: [], morphs: [Morph(ich), Morph(Ist)] ),
Chunk( id: 1, dst: 2, srcs: [], morphs: [Morph(Hier), Morph(damit)] ),
Chunk( id: 2, dst: 3, srcs: ['1'], morphs: [Morph(Start), Morph(Hand)] ),
Chunk( id: 3, dst: 4, srcs: ['2'], morphs: [Morph(Mensch), Morph(Das)] ),
Chunk( id: 4, dst: 5, srcs: ['3'], morphs: [Morph(Ding), Morph(Zu)] ),
Chunk( id: 5, dst: -1, srcs: ['0', '4'], morphs: [Morph(Sie sehen), Morph(Ta), Morph(。)] )]
"""
chunks_surface = []
for chunk in chunks:
if len(chunk.srcs) == 0:
continue
else:
current_chunk_surface = concat_morphs_surface(chunk)
for src in chunk.srcs:
src_chunk = chunks[int(src)]
src_chunk_surface = concat_morphs_surface(src_chunk)
chunks_surface.append(
"{} {}".format(src_chunk_surface, current_chunk_surface)
)
return chunks_surface
fpath = "neko.txt.cabocha"
sentences = read_file(fpath)
chunks = [convert_sent_to_chunks(sent) for sent in sentences] # ans41
result = [concat_chunks_surface(sent) for sent in chunks] # ans42
result = list(filter(lambda x: len(x) != 0, result)) # filtering the empty list
for sent in result[:3]:
print(sent)
# ['ich bin eine Katze']
# ['Kein Name', 'Noch nicht']
# ['Wo wurdest du geboren', 'Geboren oder nicht', 'Ich verstehe es nicht', 'Ich habe keine Ahnung']
Recommended Posts