Comments on: The Search for Meaning http://thenoisychannel.com/2008/04/17/the-search-for-meaning/ Sat, 11 Feb 2012 00:39:47 +0000 hourly 1 http://wordpress.org/?v=3.3.1 By: Search Innovation: Why Can’t We All Just Get Along? | The Noisy Channel http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-3923 Search Innovation: Why Can’t We All Just Get Along? | The Noisy Channel Fri, 26 Jun 2009 16:21:57 +0000 http://thenoisychannel.com/?p=10#comment-3923 [...] like the folks at Hakia (I blogged about them a while ago), but here I think they’re over-reacting, at least. The idea of using [...] [...] like the folks at Hakia (I blogged about them a while ago), but here I think they’re over-reacting, at least. The idea of using [...]

]]> By: Daniel Tunkelang http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-62 Daniel Tunkelang Tue, 20 May 2008 13:22:00 +0000 http://thenoisychannel.com/?p=10#comment-62 Elder, I've read my share of ACL papers, and I have no doubt that the computational linguistics community is doing great work. But even you refer to "NLP that is being developed" to achieve natural language dialog with computers. In other words, we're certainly not there, and not for lack of trying. You seem sure that we will get there if we keep trying. Maybe. I'm just not as convinced, for the reasons I've described. But the kind of dialog I am advocating is hardly pre-canned. Rather, I'd like to see us preserve the flexibility of natural language while exorcising its ambiguity. Perhaps that's as aspirational as the quest for natural language dialog, but I think we should draw insight from the successful track record of formal languages for human-computer interaction (e.g., programming languages), as compared to that of natural language. Elder, I’ve read my share of ACL papers, and I have no doubt that the computational linguistics community is doing great work. But even you refer to “NLP that is being developed” to achieve natural language dialog with computers. In other words, we’re certainly not there, and not for lack of trying. You seem sure that we will get there if we keep trying. Maybe. I’m just not as convinced, for the reasons I’ve described. But the kind of dialog I am advocating is hardly pre-canned. Rather, I’d like to see us preserve the flexibility of natural language while exorcising its ambiguity. Perhaps that’s as aspirational as the quest for natural language dialog, but I think we should draw insight from the successful track record of formal languages for human-computer interaction (e.g., programming languages), as compared to that of natural language.

]]> By: Elder http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-61 Elder Mon, 19 May 2008 12:10:00 +0000 http://thenoisychannel.com/?p=10#comment-61 I, too, believe strongly in dialogic interfaces and so I find your position on NLP distinctly odd. It may be the case that there are drawbacks for humans to communicate in Natural languages -- I for one have very little idea how else a mother would communicate with her infant to introduce the child to the world, but, heh -- but I guess I will fall back on the old saw about democracy: it may be flawed, but it's the best we've got. So, if we are going to dialog with computers, dialoging in natural languages with all the bells and whistles --anaphora, ellipsis, push/pop to from embedded segments, entrainment to the other in terms of lexis, syntax, the lot-- is probably the "most efficient" way to go about it. All that leads to NLP as the enabling technology. Not the NLP that at the moment is deployed in Powerset or Hakia but the NLP that is supported by these technologies, NLP that is being developed at a thousand sites around the world and presented at the ACL and other confierences. Primitive "I know what you want and I'll anticipate it with stilted, pre-canned dialog" just isn't the interface of the future -- not even for information retrieval applicatons. "Sorry, Charlie." as the tuna used to say. I, too, believe strongly in dialogic interfaces and so I find your position on NLP distinctly odd. It may be the case that there are drawbacks for humans to communicate in Natural languages — I for one have very little idea how else a mother would communicate with her infant to introduce the child to the world, but, heh — but I guess I will fall back on the old saw about democracy: it may be flawed, but it’s the best we’ve got. So, if we are going to dialog with computers, dialoging in natural languages with all the bells and whistles –anaphora, ellipsis, push/pop to from embedded segments, entrainment to the other in terms of lexis, syntax, the lot– is probably the “most efficient” way to go about it. All that leads to NLP as the enabling technology. Not the NLP that at the moment is deployed in Powerset or Hakia but the NLP that is supported by these technologies, NLP that is being developed at a thousand sites around the world and presented at the ACL and other confierences. Primitive “I know what you want and I’ll anticipate it with stilted, pre-canned dialog” just isn’t the interface of the future — not even for information retrieval applicatons. “Sorry, Charlie.” as the tuna used to say.

]]> By: Daniel Tunkelang http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-60 Daniel Tunkelang Sat, 17 May 2008 01:30:00 +0000 http://thenoisychannel.com/?p=10#comment-60 Stefano, thanks! To be clear, I'm all for the best and brightest minds trying to solve hard problems. I just would rather see them pursue projects whose practical consequences are at least proportional to the difficulty of the obstacles that have to be overcome. Stefano, thanks! To be clear, I’m all for the best and brightest minds trying to solve hard problems. I just would rather see them pursue projects whose practical consequences are at least proportional to the difficulty of the obstacles that have to be overcome.

]]> By: stefano http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-56 stefano Fri, 16 May 2008 14:35:00 +0000 http://thenoisychannel.com/?p=10#comment-56 Reminds me of the handwriting example. What's easier: getting a machine to recognize script or teaching a human to write legibly for mechanical readers? I find your perspective refreshing and stimulating, Daniel. Reminds me of the handwriting example. What’s easier: getting a machine to recognize script or teaching a human to write legibly for mechanical readers? I find your perspective refreshing and stimulating, Daniel.

]]> By: Daniel Tunkelang http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-43 Daniel Tunkelang Sun, 11 May 2008 14:59:00 +0000 http://thenoisychannel.com/?p=10#comment-43 Des, thanks! To be clear, I may be harsher on Powerset because of my greater familiarity with it (through the private beta) and because of the volume of hype. I'm broadly skeptical of natural language search, and even hakia's excellent presentation did not convert me. Des, thanks! To be clear, I may be harsher on Powerset because of my greater familiarity with it (through the private beta) and because of the volume of hype. I’m broadly skeptical of natural language search, and even hakia’s excellent presentation did not convert me.

]]> By: Des http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-42 Des Sun, 11 May 2008 09:02:00 +0000 http://thenoisychannel.com/?p=10#comment-42 Thoroughly interesting read. Landed while reading up on powerset and left reading the hakia slides. illuminating!<br/>-des<br/>http://techwatch.reviewk.com/ Thoroughly interesting read. Landed while reading up on powerset and left reading the hakia slides. illuminating!
-des
http://techwatch.reviewk.com/

]]> By: Daniel Tunkelang http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-29 Daniel Tunkelang Sun, 20 Apr 2008 04:00:00 +0000 http://thenoisychannel.com/?p=10#comment-29 Slides from the <a HREF="http://hakia.com/" REL="nofollow">hakia</a> talk are available on the <a HREF="http://www.swnyc.org/index.php?title=Slides" REL="nofollow">Semantic Web NYC web site</a>. Slides from the hakia talk are available on the Semantic Web NYC web site.

]]> By: Jon http://thenoisychannel.com/2008/04/17/the-search-for-meaning/comment-page-1/#comment-28 Jon Fri, 18 Apr 2008 12:07:00 +0000 http://thenoisychannel.com/?p=10#comment-28 Daniel - Nice to see someone having the same reaction as I: "I see no evidence that they have produced better results than keyword search"<br/><br/>I have to admit, I was trying out all of Kaplan's demo examples on both Powerset & Google during his talk. I didn't find a single one that I would say Powerset more effectively handled than Google. Keep in mind these were hand-picked examples to show the power of NL search.<br/><br/>I will say that Wikipedia has changed the game for both Powerset and Google. For Powerset, it provides a mostly well formed and factual resource for their NLP. For Google, by either design or chance, its in the top 10 results for most queries. If the topic of the Wikipedia page is right and finding an answer to your question in that page isn't too tough, this effectively circumvents the need for any real NLP. Daniel – Nice to see someone having the same reaction as I: “I see no evidence that they have produced better results than keyword search”

I have to admit, I was trying out all of Kaplan’s demo examples on both Powerset & Google during his talk. I didn’t find a single one that I would say Powerset more effectively handled than Google. Keep in mind these were hand-picked examples to show the power of NL search.

I will say that Wikipedia has changed the game for both Powerset and Google. For Powerset, it provides a mostly well formed and factual resource for their NLP. For Google, by either design or chance, its in the top 10 results for most queries. If the topic of the Wikipedia page is right and finding an answer to your question in that page isn’t too tough, this effectively circumvents the need for any real NLP.

]]>