Clarify a comment regarding the SD version of the multiple NMLs all b…

…ecoming nn relations. Add the same relation to the UD version of the converter
stanfordnlp · Aug 8, 2023 · 5e748dc · 5e748dc
1 parent 8e7ba0e
commit 5e748dc
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/src/edu/stanford/nlp/trees/EnglishGrammaticalRelations.java b/src/edu/stanford/nlp/trees/EnglishGrammaticalRelations.java
@@ -1019,7 +1019,7 @@ private EnglishGrammaticalRelations() {}
  new GrammaticalRelation(Language.English, "nn", "nn modifier",
  MODIFIER, "(?:WH)?(?:NP|NX|NAC|NML|ADVP|ADJP)(?:-TMP|-ADV)?", tregexCompiler,
  "/^(?:WH)?(?:NP|NX|NAC|NML)(?:-TMP|-ADV)?$/ < (NP|NN|NNS|NNP|NNPS|FW|AFX=target $++ NN|NNS|NNP|NNPS|FW|CD=sister !<<- POS !<<- (VBZ < /^[\'’]s$/) !$- /^,$/ !$++ (POS $++ =sister))",
- // same thing as the above, but without the comma. NML in such a situation is typically a noun phrase modifying a noun,
+ // same thing as the above, but without the clause excluding the comma. NML in such a situation is typically a noun phrase modifying a noun,
  // whereas other nodes such as NN can be parts of lists or otherwise unsuitable for the nn relationship
  "/^(?:WH)?(?:NP|NX|NAC|NML)(?:-TMP|-ADV)?$/ < (NML=target $++ NN|NNS|NNP|NNPS|FW|CD=sister !<<- POS !<<- (VBZ < /^[\'’]s$/) !$++ (POS $++ =sister))",
  "/^(?:WH)?(?:NP|NX|NAC|NML)(?:-TMP|-ADV)?$/ < JJ|JJR|JJS=sister < (NP|NML|NN|NNS|NNP|NNPS|FW=target !<<- POS !<<- (VBZ < /^[\'’]s$/) $+ =sister) <# NN|NNS|NNP|NNPS !<<- POS !<<- (VBZ < /^[\'’]s$/) ",

diff --git a/src/edu/stanford/nlp/trees/UniversalEnglishGrammaticalRelations.java b/src/edu/stanford/nlp/trees/UniversalEnglishGrammaticalRelations.java
@@ -921,7 +921,10 @@ private UniversalEnglishGrammaticalRelations() {}
  public static final GrammaticalRelation COMPOUND_MODIFIER =
  new GrammaticalRelation(Language.UniversalEnglish, "compound", "compound modifier",
  MODIFIER, "(?:WH)?(?:NP|NX|NAC|NML|ADVP|ADJP|QP)(?:-TMP|-ADV)?", tregexCompiler,
- "/^(?:WH)?(?:NP|NX|NAC|NML)(?:-TMP|-ADV)?$/ < (NP|NML|NN|NNS|NNP|NNPS|FW|AFX=target $++ NN|NNS|NNP|NNPS|FW|CD=sister !<<- POS !<<- (VBZ < /^[\'’]s$/) !$- /^,$/ !$++ (POS $++ =sister))",
+ "/^(?:WH)?(?:NP|NX|NAC|NML)(?:-TMP|-ADV)?$/ < (NP|NN|NNS|NNP|NNPS|FW|AFX=target $++ NN|NNS|NNP|NNPS|FW|CD=sister !<<- POS !<<- (VBZ < /^[\'’]s$/) !$- /^,$/ !$++ (POS $++ =sister))",
+ // same thing as the above, but without the clause excluding the comma. NML in such a situation is typically a noun phrase modifying a noun,
+ // whereas other nodes such as NN can be parts of lists or otherwise unsuitable for the nn relationship
+ "/^(?:WH)?(?:NP|NX|NAC|NML)(?:-TMP|-ADV)?$/ < (NML=target $++ NN|NNS|NNP|NNPS|FW|CD=sister !<<- POS !<<- (VBZ < /^[\'’]s$/) !$++ (POS $++ =sister))",
  "/^(?:WH)?(?:NP|NX|NAC|NML)(?:-TMP|-ADV)?$/ < JJ|JJR|JJS=sister < (NP|NML|NN|NNS|NNP|NNPS|FW=target !<<- POS !<<- (VBZ < /^[\'’]s$/) $+ =sister) <# NN|NNS|NNP|NNPS !<<- POS !<<- (VBZ < /^[\'’]s$/) ",
  "QP|ADJP < (/^(?:CD|$|#)$/=target !$- CC)", //number relation in original SD
  "@NP < (/^[$]$/=target $+ /^N.*/)",