The CposErrorAnalyzer tallies coarse part-of-speech tagging errors according to the specific error (i.e.
Shorthand for the PathAccuracyScore ignoring punctuation, and using breadcrumbs only for path equivalence.
Counts the number of tokens "lost" by bad attachments (i.e.
Counts the number of tokens "lost" by bad attachments (i.e. their path to the root is different in the gold and candidate parse).
Shorthand for the PathAccuracyScore ignoring punctuation.
The LostTokensAnalyzer tallies lost tokens (i.e.
The LostTokensAnalyzer tallies lost tokens (i.e. tokens with a different breadcrumb path in the gold parse) according to the breadcrumb arc label of their highest misattached ancestor in the gold parse.
Example: In the gold parse, suppose the breadcrumb path of token "red" is
--ROOT--> ate --PREP--> with --POBJ--> chopsticks --AMOD--> red
but in the candidate parse, the breadcrumb path of token "chopsticks" is
--ROOT--> ate --DOBJ--> pasta --PREP--> with --POBJ--> meatballs --AMOD--> red
then the highest misattached ancestor of "red" in the gold parse is "with" (attached to "pasta" instead of "ate"). The arc label of "with" is "PREP" in the gold parse. So the loss of token "red" is attributed to a "PREP" attachment error.
a bank containing the gold parses
The MisattachmentAnalyzer tallies misattached tokens (i.e.
The MisattachmentAnalyzer tallies misattached tokens (i.e. tokens with the wrong breadcrumb assignment) according to the label of its breadcrumb arc in the gold parse.
a bank containing the gold parses
set to true if we want to regard a node as correctly attached as long as its breadcrumb is correct (regardless of how its breadcrumb arc is labeled)
A ParseAnalyzer maps a candidate parse to an "analysis", i.e.
A ParseAnalyzer maps a candidate parse to an "analysis", i.e. a histogram.
For instance, this histogram may be the count of mistaken arclabels or part-of-speech tags.
A ParseBank maps string-representations of sentences to a unique parse.
A ParseBank maps string-representations of sentences to a unique parse.
the map from strings to parses
A ParseScore maps a candidate parse to a score.
The PathAccuracyScore computes the percentage of a candidate parse's tokens that have a completely correct breadcrumb path (i.e.
The PathAccuracyScore computes the percentage of a candidate parse's tokens that have a completely correct breadcrumb path (i.e. if you follow a token's breadcrumbs to the nexus in both the candidate and the gold parse, you encounter the same set of tokens in the same order).
Counts the fraction of correctly labeled coarse part-of-speech tags in a candidate parse.
Counts the fraction of correctly labeled coarse part-of-speech tags in a candidate parse.
the bank containing the gold parses
Shorthand for the PathAccuracyScore ignoring path labels, punctuation, and using breadcrumbs only for path equivalence.
Counts the number of tokens "lost" by bad attachments (i.e.
Counts the number of tokens "lost" by bad attachments (i.e. their path to the root is different in the gold and candidate parse). This version ignores arc labels for the purpose of path equivalence.
Shorthand for the PathAccuracyScore ignoring path labels and punctuation.
The CposErrorAnalyzer tallies coarse part-of-speech tagging errors according to the specific error (i.e. "NOUN-->VERB" means that a NOUN was incorrectly tagged as a verb).
a bank containing the gold parses