Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

QuestionToStatementTranslator #1235

Unanswered
sudvijayr-nlp asked this question in Q&A
Discussion options

QuestionToStatementTranslator is not generating statements for few specific questions, are these known issues?
Here is an example,
/usr/bin/java edu.stanford.nlp.naturalli.QuestionToStatementTranslator
[main] INFO edu.stanford.nlp.pipeline.StanfordCoreNLP - Adding annotator tokenize
[main] INFO edu.stanford.nlp.pipeline.StanfordCoreNLP - Adding annotator ssplit
[main] INFO edu.stanford.nlp.pipeline.StanfordCoreNLP - Adding annotator pos
[main] INFO edu.stanford.nlp.tagger.maxent.MaxentTagger - Loading POS tagger from edu/stanford/nlp/models/pos-tagger/english-left3words/english-left3words-distsim.tagger ... done [1.0 sec].
[main] INFO edu.stanford.nlp.pipeline.StanfordCoreNLP - Adding annotator lemma
question> who killed Tom?
question>

Questions like above don't generate responses. i'm checking the code, are these known issues?

You must be logged in to vote

Replies: 2 comments 1 reply

Comment options

I didn't even know this existed, and now that I do, I have no desire to attempt to work on it. It looks like this is based on a bunch of deterministic rules, and simply put, they don't have enough coverage. Here is a brief sample of how well it works...

I'll ask briefly if anyone knows of a different solution

question> Where was Tom born?
 -> Tom was born at location
question> Where did Tom die?
 -> Tom die at location
question> Who killed Tom?
question> Where were you when Tom was killed?
 -> were you when Tom was killed at location
question> How much wood could a woodchuck chuck if a woodchuck could chuck wood?
question> Does this actually do anything?
question> What state is north of New Jersey?
 -> north of New Jersey is state
question> What does duck taste like?
 -> duck taste like thing
question> Will the Flyers win this shootout?
question> Is this game over?
question> Are you holding on?
question> Are you depressed that she's gone?
question> What beautiful mistakes did you make?
 -> you make beautiful mistakes
question> Who is naked in my bed?
 -> naked in my bed is person
question> Who lies awake?
question> Would you take them back?
question> Why is Mox Opal banned?
question> Where can I meet Andorian women?
question> What color are Andorians?
 -> Andorians are color
question> What is this crap?
 -> thing is this crap
You must be logged in to vote
1 reply
Comment options

Exactly it is based on few deterministic rules, namely thing, location, person, time. I will get it in a while and have it fixed. Meanwhile any suggestions will help.

Comment options

If you have any suggestions for improvement, happy to hear them!
...
On Tue, Dec 21, 2021 at 11:22 PM sudvijayr-nlp ***@***.***> wrote: Exactly it is based on few deterministic rules, namely thing, location, person, time. I will get it in a while and have it fixed. Meanwhile any suggestions will help. — Reply to this email directly, view it on GitHub <#1235 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AA2AYWJ6B6Z73MDBCSBSWQTUSF4FBANCNFSM5KGOIHAA> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you commented.Message ID: ***@***.***>
You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet

AltStyle によって変換されたページ (->オリジナル) /