Google squared

Matt Hurst published some results today of some of his own experiments with Google^2.  It's kind of interesting to compare Google^2 to SEAL, which has more limited goals (it doesn't try and find attributes).   I don't think either one is clearly superior, from my trials, but it seems like SEAL does quite well comparatively.

Matt's first query, "small boats" gives mediocre results for Google^2, but SEAL gives

#	Found Items
1	Kayaks
2	Dinghies
3	Kayak
4	Catamarans
5	Canoe
6	Sunfish
7	rowboats
8	Sailboats
9	Laser
10	Daysailers

which is quite decent (modulo kayak and kayaks being the same).  "Sailing boats" gives spottier results in SEAL:

#	Found Items
1	Yachts
2	Catamarans
3	Catamaran
4	Dinghies
5	Sailing Yachts
6	Beneteau
7	Mega Yachts
8	Dinghy
9	Yacht
10	Optimist

SEAL's result for "netbooks" is great, except "linux" creeps in somewhere in the top 30 results...

#	Found Items
1	Samsung NC10
2	Acer Aspire One
3	Lenovo IdeaPad S10
4	Dell Inspiron Mini 9
5	HP Mini 1000
6	Asus Eee PC 901
7	asus-eee-pc-1000h
8	MSI Wind
9	MSI Wind U100
10	Dell Inspiron Mini 12
11	asus-eee-pc-900
12	Toshiba NB100
13	samsung-n120
14	HP Mini 2140
15	asus-eee-pc-s101
16	asus-eee-pc-1000he
17	msi-wind-u123
18	Samsung NC20
19	sony-vaio-p
20	archos-10
21	hp-mini-note-2133
22	Asus Eee PC 1000
23	Samsung N310
24	Linux
25	MSI Wind U120
26	Samsung N110
27	ASUS Eee PC 1002HA
28	Asus Eee PC T91
29	Asus Eee PC 900A
30	Dell Inspiron Mini 10

"Scottish regions" gives mostly cities in SEAL (like in Google^2), to the extent that I can recognize what it gives.  Matt's next queries are:

Test 5: ‘british overseas territories’ – SEAL gives a very reasonable list, as does Google^2, according to Matt.

Test 6: ‘plants native to the pacific northwest’ – Matt rates Google^2 as "very poor {gardening, botany, Hardcover, Your account, Add your first tag, Share your own customer images, paperback)".  SEAL starts with "Trees, Plant nursery, Washington" and then goes downhill....but it at least knows that it didn't find much and tells you that the list has low confidence.

Test 7: ‘novels of o’brian’ – excellent results from Google^2, and mediocre low-confidence results from SEAL.

Test 8: ‘jedi masters’ – Matt's comments for Google^2 is "oops {Obi-Wan kenobi, Star Wars: The Clone Wars, Mace Windu, Star Wars Episode VI:return of the jedi, Jedi Temple, Kit Fisto, Younglings}".  SEAL gives

#	Found Items
1	Mace Windu
2	Obi-Wan Kenobi
3	Luke Skywalker
4	Yoda
5	Qui-Gon Jinn
6	Ki-Adi-Mundi
7	Shaak Ti
8	Jedi Council
9	Plo Koon
10	Saesee Tiin

Nice, except for #8, but why is Mace-Windu first? still, this is pretty good.

Test 9: ‘movies of brad pitt’ – Google^2 gets "not bad, a reasonable list of movies with Director and Language fields. Note that it doesn’t attempt to normalize ‘USA’ and ‘United States’ suggesting that the system uses very superficial representations internally."  SEAL gets poor results, with a low-confidence warning.

Test 10: ‘progressive rock bands’ – Google^2 gets a "fail" from Matt.  SEAL gets

#	Found Items
1	Yes
2	Pink Floyd
3	King Crimson
4	Genesis
5	Rush
6	Jethro Tull
7	Gentle Giant
8	Dream Theater
9	Jazz
10	Van Der Graaf Generator
11	Marillion
12	Camel
13	The Beatles
14	Porcupine Tree
15	Procol Harum
16	Kansas
17	Frank Zappa
18	Led Zeppelin
19	Magma
20	Art rock
21	The Moody Blues
22	Deep Purple
23	Tool
24	Tangerine Dream
25	The Mars Volta
26	Punk rock
27	Progressive metal
28	Classical music
29	The Wall
30	Symphonic rock