TechCrunch writes about a new calendaring service: SpongeCell. The description mentions the use of NLP to grok free text entries to the caledar, so I had to give it a shot:
- Visiting Granny at 12 on March 1st: no problem, off to a good start.
- Flying to Cambridge on the 2nd then back on the 4th: sweet - it got the two dates. They were placed in February, so no context (my last entry was March), but that is probably the right behaviour.
- Flying to Boston tomorrow: this got entered in today's field, could be a time zone problem. It is 2am on the 31st where I am, so the entry should have been on the 1st of February.
- Flying to Boston in a week: nope, turned up in yesterday's list. Could be related to the issue above in that it really meant to put it in today's list - either way it's wrong.
- Flying to Boston on Thursday: no problem.
- Flying to Boston a week on Thursday: nope - just Thursday.
- Flying to Boston on the 30th of Feb: oops - turns up on the 2nd of March. An understandable error, but certainly a corner case that needs to be addressed.
In summary, the NLP does a reasonable job. However, there is always a danger with this type of interface that the user will learn what can and can't be entered and then restrict their input to a closed set of patterns - essentially a controlled language for date entry. This doesn't actually undermine the utility of the input method (think of the Graffiti method to input text into a Palm device).