Working on anaphora resolution

README.log

@@ -0,0 +1,47 @@
+This is pdfTeX, Version 3.1415926-2.4-1.40.13 (TeX Live 2012) (format=pdflatex 2012.6.30)  5 APR 2013 02:11
+entering extended mode
+ restricted \write18 enabled.
+ file:line:error style messages enabled.
+ %&-line parsing enabled.
+**README.md
+(./README.md
+LaTeX2e <2011/06/27>
+Babel <v3.8m> and hyphenation patterns for english, dumylang, nohyphenation, ge
+rman-x-2012-05-30, ngerman-x-2012-05-30, afrikaans, ancientgreek, ibycus, arabi
+c, armenian, basque, bulgarian, catalan, pinyin, coptic, croatian, czech, danis
+h, dutch, ukenglish, usenglishmax, esperanto, estonian, ethiopic, farsi, finnis
+h, french, friulan, galician, german, ngerman, swissgerman, monogreek, greek, h
+ungarian, icelandic, assamese, bengali, gujarati, hindi, kannada, malayalam, ma
+rathi, oriya, panjabi, tamil, telugu, indonesian, interlingua, irish, italian, 
+kurmanji, latin, latvian, lithuanian, mongolian, mongolianlmc, bokmal, nynorsk,
+ polish, portuguese, romanian, romansh, russian, sanskrit, serbian, serbianc, s
+lovak, slovenian, spanish, swedish, turkish, turkmen, ukrainian, uppersorbian, 
+welsh, loaded.
+
+./README.md:1: LaTeX Error: Missing \begin{document}.
+
+See the LaTeX manual or LaTeX Companion for explanation.
+Type  H <return>  for immediate help.
+ ...                                              
+
+l.1 A
+     RKref
+? 
+./README.md:1: Emergency stop.
+ ...                                              
+
+l.1 A
+     RKref
+You're in trouble here.  Try typing  <return>  to proceed.
+If that doesn't work, type  X <return>  to quit.
+
+
+Here is how much of TeX's memory you used:
+ 7 strings out of 493488
+ 256 string characters out of 3141326
+ 49432 words of memory out of 3000000
+ 3412 multiletter control sequences out of 15000+200000
+ 3640 words of font info for 14 fonts, out of 3000000 for 9000
+ 957 hyphenation exceptions out of 8191
+ 5i,0n,4p,18b,14s stack positions out of 5000i,500n,10000p,200000b,50000s
+./README.md:1:  ==> Fatal error occurred, no output PDF file produced!

answer

@@ -13,7 +13,7 @@ import re
 import itertools
 import nltk
 from nltk.stem import PorterStemmer
-from bs4 import BeautifulSoup
+import bs4
 # Import our modules from /modules
 sys.path.append("modules")
 import questionClassifier
@@ -27,16 +27,24 @@ def contains_negative(sent):
 
 # the set of pronouns, used for anaphora resolution
 pronouns = set(["he", "she", "it", "him", "her", "his","they","their","we",
-                "our","I","you","your","my","mine","yours","ours"])
+                "our","i","you","your","my","mine","yours","ours"])
 
 # Runs coreference resolution on the article using arkref.
 # This still needs to be implemented.
 def coref(path_to_article):
   subprocess.call(["./arkref.sh", "-input", path_to_article])
   tagged_article = open(path_to_article.replace("txt", "tagged")).read()
   tagged_article = "<root>"+tagged_article+"</root>"
-  soup = BeautifulSoup(tagged_article, "xml")
-  print soup.prettify()
+  print tagged_article
+  soup = bs4.BeautifulSoup(tagged_article, "html.parser").root
+  for entity in soup.find_all(True):
+    if entity.string != None and entity.string.strip().lower() in pronouns:
+      antecedent_id = entity["entityid"].split("_")[0]
+      antecedent = soup.find(mentionid=antecedent_id)
+      #entity.string.replace_with(antecedent)
+      print antecedent
+    #entity.unwrap()
+
   return open(path_to_article).read()
 
 # Answers a question from the information in article.
@@ -83,4 +91,4 @@ if __name__ == '__main__':
       print "Our answer:", answer(question, article)
       print "Correct answer:", correct_answer
 
-    print
+    print