#!/usr/bin/env python
import nltk
import init
import chunker
#returns 1 if the character following the answer in the document is one of <, . " : !>
#and returns 0 otherwise
def punc_loc(question, (answer, doc_num, index, features, q_id)):
doc = chunker.clean_punctuation(init.get_doc(doc_num))
answer = chunker.clean_punctuation(answer)
#go to index location of candidate within the document
alist = answer.split(
) #split candidate answer into words (space delimiter)
answer_len = len(alist) #word length of the candidate answer
#print answer_len
punc_word_index = index + answer_len #index of the word that may contain the punctuation
dlist = doc.split() #split the document by words
punc_word = dlist[punc_word_index] #getting the actual word from the doc
#check if that lastcharacter is a punctuation
if punc_word == ',' or punc_word == '.' or punc_word == '"' or punc_word == ':' or punc_word == '!':
return 1
else:
return 0
#test case below was modified to work with specified doc instead of the actual doc to work with a known index
def test():
import init
import chunker
import read_questions
import sys
MAX_INT = sys.maxint
def literal_question_distance(question, (answer, doc_num, index, features,
q_id)):
"""Evaluates a candidate based on how close it is to the longest fragment of
the question in the document
returns (distance, length of fragment)
"""
doc = chunker.clean_punctuation(init.get_doc(doc_num))
(start, _, length) = find_match(question, doc)
words = doc.split()
index = len(" ".join(words[0:index + 1]))
return (min(abs(start - index), abs(start + length - index),
0 if start <= index <= start + length else MAX_INT), length)
def literal_rewrite_distance(question, candidate):
"""Evaluates a candidate based on how close it is to the longest fragment of
the re-written question in the document
returns (distance, length of fragment)
"""
return literal_question_distance(rewriteQuestion(question), candidate)
from difflib import SequenceMatcher as SequenceMatcher
import init
import chunker
import read_questions
import sys
MAX_INT = sys.maxint
def literal_question_distance(question, (answer, doc_num, index, features, q_id)):
"""Evaluates a candidate based on how close it is to the longest fragment of
the question in the document
returns (distance, length of fragment)
"""
doc = chunker.clean_punctuation(init.get_doc(doc_num))
(start, _, length) = find_match(question, doc)
words = doc.split()
index = len(" ".join(words[0 : index + 1]))
return (
min(abs(start - index), abs(start + length - index), 0 if start <= index <= start + length else MAX_INT),
length,
)
def literal_rewrite_distance(question, candidate):
"""Evaluates a candidate based on how close it is to the longest fragment of
the re-written question in the document
returns (distance, length of fragment)
"""
#!/usr/bin/env python
import nltk
import init
import chunker
#returns 1 if the character following the answer in the document is one of <, . " : !>
#and returns 0 otherwise
def punc_loc(question, (answer, doc_num, index, features,q_id)):
doc = chunker.clean_punctuation(init.get_doc(doc_num))
answer = chunker.clean_punctuation(answer)
#go to index location of candidate within the document
alist = answer.split() #split candidate answer into words (space delimiter)
answer_len = len(alist) #word length of the candidate answer
#print answer_len
punc_word_index = index+answer_len #index of the word that may contain the punctuation
dlist = doc.split() #split the document by words
punc_word = dlist[punc_word_index] #getting the actual word from the doc
#check if that lastcharacter is a punctuation
if punc_word == ',' or punc_word == '.' or punc_word == '"' or punc_word == ':' or punc_word == '!':
return 1
else:
return 0
#test case below was modified to work with specified doc instead of the actual doc to work with a known index
def test():
question = 'What was the name, of the first Russian astronaut to do a spacewalk?'
doc = 'The name of the first Russian astronaut to do a spacewalk is Aleksei A. Leonov!'
doc_num = "LA072490-0034"
