You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
consider
sent1="X drives too fast" and
sent2="X is pulled over by a cop"
Now we know "sent1 "happens before" sent2" is true. Is there any zero-shot way of finding out whether this is true or not?
Also What if in ATOMIC, we have sent1 -> r1 -> r2 -> ... -> rk -> sent2? Is there a way to find out about this from COMET? I don't want to know this from ATOMIC because well sent1 and sent2 can be sentences outside of ATOMIC. That's where COMET would be useful.
The text was updated successfully, but these errors were encountered:
Hi @theartpiece you can refer to this paper, specifically section 3.2.1 for some ideas.
Or you could predict object phrases using the premise and search for a semantic match for the hypothesis. For your eg, you would pass "X drives too fast" to COMET, search the "object phrase" outputs (for suitably predictive ATOMIC relations) to match with "X is pulled over by a cop". However with this you'll be able to predict entailment only. For contradiction you could negate your hypothesis and do the same process.
Take this with a grain of salt, just a possible approach that came to mind :)
consider
sent1="X drives too fast" and
sent2="X is pulled over by a cop"
Now we know "sent1 "happens before" sent2" is true. Is there any zero-shot way of finding out whether this is true or not?
Also What if in ATOMIC, we have sent1 -> r1 -> r2 -> ... -> rk -> sent2? Is there a way to find out about this from COMET? I don't want to know this from ATOMIC because well sent1 and sent2 can be sentences outside of ATOMIC. That's where COMET would be useful.
The text was updated successfully, but these errors were encountered: