srl taggin pipeline (output in .tsv)

tools/parser/parser.py

@@ -1,6 +1,9 @@
 from lxml import etree
 import re
 from parser.msd.msdmap import Msdmap
+import pickle
+from pathlib import Path
+from fillpred_model.step1 import build_model_row
 
 class Parser:
     # reads a TEI xml file and returns a dictionary:
@@ -15,6 +18,8 @@ class Parser:
         self.W_TAGS = ['w']
         self.C_TAGS = ['c']
         self.S_TAGS = ['S', 'pc']
+        with Path("./fillpred_model/model.pickle").open("rb") as fp:
+            self.fillpred_model = pickle.load(fp)
 
     def parse_tei(self, filepath):
 
@@ -111,11 +116,11 @@ class Parser:
 
     def to_conll_2009_SRL(self, sentence_entry, napreds=9):
 
-        def fillpred(pos, feat):
-            # TODO (decision tree or bayes on mate training data)
-            if pos == "V" and "main" in feat.split("|"):
-                return True
-            return False
+        def fillpred(tsv_row):
+            mrow = build_model_row(tsv_row)
+            x = mrow[:-1] 
+            y = self.fillpred_model.predict([x])
+            return y[0]  # bool
 
         apreds_string = '\t'.join(["_" for x in range(napreds)])
 
@@ -137,7 +142,6 @@ class Parser:
 
             pos = self.msdmap.slo_msd_to_eng_pos(token[4])
             feat = "|".join(self.msdmap.slo_msd_to_eng_long(token[4]).split(" "))
-            fprd = fillpred(pos, feat)
 
             """
             print(t_id)
@@ -146,10 +150,7 @@ class Parser:
             print(token)
             print(sentence_entry["links"])
             """
-
-            # format: 14 + apreds
-            out_str += '\t'.join(map(str, 
-                [
+            row_list = [
                     t_id,
                     form,
                     token[3],  # lemma
@@ -162,11 +163,18 @@ class Parser:
                     sentence_entry["links"][t_id][2],  # phead
                     sentence_entry["links"][t_id][0],  # deprel
                     sentence_entry["links"][t_id][0],  # pdeprel
-                    "Y" if fprd else "_",  # fillpred
-                    token[3] if fprd else "_",  # pred
+                    "_",  # fillpred
+                    "_",  # pred
                     apreds_string,
                     "\n",
-                ]
+            ]
+            fprd = fillpred(row_list)
+            row_list[12] = "Y" if fprd else "_"
+            row_list[13] = token[3] if fprd else "_"
+
+            # format: 14 + apreds
+            out_str += '\t'.join(map(str, 
+                row_list
             ))
         out_str += "\n"  # newline at the end of sentence
         return out_str