@ -45,3 +45,6 @@ After applying multi-prompt methods like *prompt ensemble* and *prompt augmentat
Higher JGA* scores suggest the current methods of extracting value candidates need improvements.
### Value Extraction
Stanford CoreNLP client [stanza](https://stanfordnlp.github.io/stanza/index.html) is used to extract the values from user utterances. A set of rules are used to extract values from POS tags and named entities. Considering all Adjectives (JJ) and Adverbs (RB) can lead to a lot of false positives in value candidates (even after filtering out common stopwords). Another drawback of this approach is extracting the values for slots like *parking* and *internet*. When the user asks for *free* internet and *free* parking, the current belief state annotations use "yes" as the value, while the value extraction rules can only extract "free" from user utterance. This is also a drawback of the existing annotations in MultiWoZ dataset.
