"""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)
def align_question_distance(question, (answer, doc_num, index, features, q_id)):
"""Evaluates a candidate based on how close it is to the alignment of the
question in the document
returns (distance, score)
"""
doc = chunker.clean_punctuation(init.get_doc(doc_num))
(score, q, d, (q_start, d_start), (q_end, d_end)) = sw_align(question, doc)
words = doc.split()
index = len(" ".join(words[0 : index + 1]))
return (min(abs(d_start - index), abs(d_end - index), 0 if d_start <= index <= d_end else MAX_INT), score)
def align_rewrite_distance(question, candidate):
"""Evaluates a candidate based on how close it is to the alignment of the
re-written question in the document
returns (distance, score)
"""
return align_question_distance(rewriteQuestion(question), candidate)
def rewriteQuestion(question):
#!/usr/bin/env python
from align import sw_align
from question_rewrite import rewriteQuestion
import init
def question_apposition(question, (answer, doc_num, index, features,q_id)):
doc = init.get_doc(doc_num)
apposition = question + ", " + answer + ","
plain = question + " " + answer
(app_score, app, doc_app, starts, ends) = sw_align(apposition, doc)
(plain_score, pl, doc_pl, starts, ends) = sw_align(plain, doc)
return [max(0, app_score - plain_score)]
def rewrite_apposition(question, candidate):
return question_apposition(rewriteQuestion(question), candidate)
if __name__ == "__main__":
init.get_corpus(qNum=209)
question = "Who is the inventor of the phonograph?"
doc = "SJMN91-06010225"
print question_apposition(question, ("joe smith", doc, 700, {}))
print rewrite_apposition(question, ("joe smith", doc, 700, {}))
the re-written question in the document
returns (distance, length of fragment)
"""
return literal_question_distance(rewriteQuestion(question), candidate)
def align_question_distance(question, (answer, doc_num, index, features,
q_id)):
"""Evaluates a candidate based on how close it is to the alignment of the
question in the document
returns (distance, score)
"""
doc = chunker.clean_punctuation(init.get_doc(doc_num))
(score, q, d, (q_start, d_start), (q_end, d_end)) = sw_align(question, doc)
words = doc.split()
index = len(" ".join(words[0:index + 1]))
print q
print d
return (min(abs(d_start - index), abs(d_end - index),
0 if d_start <= index <= d_end else MAX_INT), score)
def align_rewrite_distance(question, candidate):
"""Evaluates a candidate based on how close it is to the alignment of the
re-written question in the document
returns (distance, score)
"""
return align_question_distance(rewriteQuestion(question), candidate)
from align import sw_align
from question_rewrite import rewriteQuestion
import init
def question_apposition(question, (answer, doc_num, index, features,q_id)):
doc = init.get_doc(doc_num)
apposition = question + ", " + answer + ","
plain = question + " " + answer
(app_score, app, doc_app, starts, ends) = sw_align(apposition, doc)
(plain_score, pl, doc_pl, starts, ends) = sw_align(plain, doc)
return max(0, app_score - plain_score)
def rewrite_apposition(question, candidate):
return question_apposition(rewriteQuestion(question), candidate)
if __name__ == "__main__":
init.get_corpus(qNum=209)
question = "Who is the inventor of the phonograph?"
doc = "SJMN91-06010225"
print question_apposition(question, ("joe smith", doc, 700, {}))
# print rewrite_apposition(question, ("joe smith", doc, 700, {}))