14 June 2009

NL Generation: A new problem

Those who talk to me a lot over the years know that I really think that generation is a cool and interesting problem, but one that is hampered by a lack of clarity of what it is, or at least what the input/output is. It's like the problem with defining summarization, but one hundred times worse.

I have no idea how it came up. I think I was talking to a bunch of people from Microsoft Research and we were talking about translation on the web and what not. And how this is not the business model of Language Weaver. And how when you're on the web you make money by advertising.

And voila! The most incredible NL Generation task occurred to me! (I apologize if you ran in to me at all during NAACL because this was pretty much all I could talk about :P.) The initial idea for the task was embedded in MT, though it needn't be. But I'll tell it in the MT setting.

So I go to some web page in some weirdo language (say, French) that I don't understand (because I was a moron and took Latin instead of French or Spanish in middle school and high school). So I ask my favorite translation system (Google or Microsoft or Babelfish or whatever) to translate it. However, the translation system takes certain liberties with the translation. In particular, it might embed a few "product placements" in the text. For instance, maybe it's translating "Je suis vraiment soif" into English (if this is incorrect, blame Google). And perhaps it decides that instead of translating this as "I'm really thirsty," it will translate it as "I'm really thirsty for a Snapple," or "I'm really thirsty: I could go for a Snapple," perhaps with a link to snapple.com.

Product placement is all over the place, even in America where it's made fun of and kept a bit at bay. Not so in China: any American remotely turned off by the Coca-cola cups from which the judges on American Idol drink twice a week would be appalled by the ridiculous (my sentiment) product placement that goes on over there. The presence of the link would probably give away that it's an ad, though of course you could leave this off.

But why limit this to translation. You could put such a piece of technology directly on blogger, or on some proxy server that you can go through to earn some extra cash browsing the web (thanks to someone -- can't remember who -- at NAACL for this latter suggestion). I mean, you could just have random ads pop up in the middle of text on any web page, for instance one you could host on webserve.ca!

(See what I did there?)

So now here's a real generation problem! You're given some text. And maybe you're even given adwords or something like that, so you can assume that the "select which thing to advertise" problem has been solved. (Yes, I know it's not.) Your job is just to insert the ad in the most natural way in the text. You could evaluate in at least two ways: click through (as is standard in a lot of this advertising business) and human judgments of naturalness. I think the point of product placement is to (a) get your product on the screen more or less constantly, rather than just during commercial breaks which most people skip anyway, and (b) perhaps appeal to people's subconscious. I don't know. My parents (used to) do advertising like things but I know next to nothing about that world.

Okay, so this is slightly tongue in cheek, but not entirely. And frankly, I wouldn't be surprised if something like it were the norm in five years. (If you want to get more fancy, insert product placements into youtube videos!)

25 comments:

Anonymous said...

That's a pretty cool idea, if a bit mercenary. Now you've sort of got me wanting to actually do this.

If I were to go about it, my steps would probably be:
1.) Cluster products: Snapple ~ Coke ~ Fanta.
2.) Mine mention templates of said products on the web ("I'm thirsty; I could really go for <beverage>").
3.) Find regions of text which "look like" an appropriate template and substitute the template for the text.

Each step seems totally do-able to me, at least as a first cut. Now if I could only find a minion to implement this for me...

hal said...

Jonathan: Sounds like what we really want is a bootstrapping approach!

abhishek said...

There are attempts to do something like this for video. Check this:

http://www.zunavision.com/

However the placement of ads is manual.

Santa Ana City Directory said...

Nice, I think it could be interesting to add some more entries following this one, and probably it's not only me having this opinion. Cheers! Please come visit my site Local Business Directory Of Santa Ana U.S.A. when you got time.

Anaheim City Directory said...

Thank you for your good humor and for allowing yourself to be convinced that this was the right show for you to work on. Please come visit my site Anaheim Yellow Page Business Directory when you got time.

jg said...

Well done, comment spammers - excellent irony.

Ben said...

How about giving that to your favorite oppressive government, paired with opinion detection, for an even more effective muzzling of the opposition.

I can't wait for the community to begin working on plain text spam detection and removal.

(BTW, "J'ai vraiment soif" is the right translation)

Atul Kulkarni said...

I am kind of in the middle of things here with this Idea of yours... As a NLP task I like it. As a consumer I might not like it. Imagine you place this a bit too much in the text of news article or something that needs concentration to read and every time you mouse over or do something you see this pop-up or balloon. I would really be mad at that, it disrupts a person's concentration. On the other hand if these adds were placed in the product descriptions of the some other related products that may help the user. Say I am shopping for a bike and then in the description it has words like "gears, traction, wire shift, fiber frame, slope, ease of maneuvering" and then we show advertisement for may be "gear oil or comfortable seat or another bike altogether" (keeping all of the conflicting interest of various competing vendors in mind) we will do a good job there in helping the users. I know I am talking in terms of the use and implementation of the idea but really if there is no use to it why explore the idea is the point I had in mind.

Salem Oregon Business Directory said...

I am not really sure if best practices have emerged around things like that, but I am sure that your great job is clearly identifed. I was wondering if you offer any subscription to your RSS feeds as I would be very interested and can't find any link to subscribe here Please come visit my site Salem Oregon Business Directory when you got time. Thanks.

Pomona California Business Directory said...

I enjoyed reading your work! GREAT post! I looked around for this… but I found you! Anyway, would you mind if I threw up a backlink from my site?
Please come visit my site Pomona California Business Directory when you got time. Thanks.

Unknown said...

Since I’m new to blogging, these articles are greatly appreciated; very useful and informative blog and every body must visit this blog. Please come visit my site Fremont Business Directory when you got time.

Unknown said...

Well, nice article buddy… Someone will love to read this infor if I tell her about this. She’s really interested in this subject. Thanks again… Please come visit my site Chicago Business Directory when you got time.

Anonymous said...

What a facinating article. I’m looking for a marketing expert to help with a project, could you help? Please come visit my site Minneapolis City Directory when you got time.

Anonymous said...

You share valuable information and excellent design you got here! I would like to thank you for sharing your thoughts and time into the stuff you post!! Thumbs up. Please come visit my site Phone Directory Of St. Paul City Minnesota MN State when you got time.

Anonymous said...

I was thinking of looking up some of them newspaper websites, but am glad I came here instead. Although glad is not quite the right word… let me just say I needed this after the incessant chatter in the media, and am grateful to you for articulating something many of us are feeling - even from distant shores. Please come visit my site Local Business Directory Of Wichita U.S.A. when you got time.

Anonymous said...

This is just another reason why I like your website. I like your style of writing you tell your stories without out sending us to 5 other sites to complete the story. Please come visit my site Fremont City Business Search Engine when you got time.

Anonymous said...

information will be very useful for me. Thanks for all your help and wishing you all the success in your business. Please come visit my site Glendale City Business Search Engine when you got time.

Anonymous said...

I really liked your blog! Please come visit my site Local Business Directory Of Nashville U.S.A. when you got time.

Anonymous said...

I really liked your blog! Please come visit my site Nashville City Directory when you got time.

Anonymous said...

I enjoyed reading your work! GREAT post! I looked around for this… but I found you! Anyway, would you mind if I threw up a backlink from my site? Please come visit my site San Francisco Phone Book when you got time.

Anonymous said...

I enjoyed reading your work! GREAT post! I looked around for this… but I found you! Anyway, would you mind if I threw up a backlink from my site? Please come visit my site San Francisco Business Directory Forum Blog Classifieds when you got time.

rr8004 said...

I wanted to thank you for this great read!! I definitely enjoying every little bit of it :) I have you bookmarked to check out new stuff you post. Please visit my Please visit my blog when you have time Please come visit my site Reno Business Phone Listing when you got time.

rr8004 said...

I wanted to thank you for this great read!! I definitely enjoying every little bit of it :) I have you bookmarked to check out new stuff you post. Please visit my Please visit my blog when you have time Please come visit my site Reno Nevada NV Directory when you got time.

Anonymous said...

Классные мультики мультфильмы бесплатно на кинозоуне.
электронная почта без регистрации

gamefan12 said...

The best company to talk to about this mirosoft. You are definitely going in the right direction.
new york mesothelioma lawyer