1
00:00:00,285 --> 00:00:03,178
This is an image of the planet Earth.

2
00:00:03,178 --> 00:00:06,271
It looks very much like the Apollo pictures

3
00:00:06,271 --> 00:00:07,882
that are very well known.

4
00:00:07,882 --> 00:00:09,952
There is something different;

5
00:00:09,952 --> 00:00:11,399
you can click on it,

6
00:00:11,399 --> 00:00:12,597
and if you click on it,

7
00:00:12,597 --> 00:00:15,669
you can zoom in on almost any place on the Earth.

8
00:00:15,669 --> 00:00:17,668
For instance, this is a bird's-eye view

9
00:00:17,668 --> 00:00:20,334
of the EPFL campus.

10
00:00:20,334 --> 00:00:22,442
In many cases, you can also see

11
00:00:22,442 --> 00:00:26,182
how a building looks from a nearby street.

12
00:00:26,182 --> 00:00:27,604
This is pretty amazing.

13
00:00:27,604 --> 00:00:31,031
But there's something missing in this wonderful tour:

14
00:00:31,031 --> 00:00:33,219
It's time.

15
00:00:33,219 --> 00:00:36,289
i'm not really sure when this picture was taken.

16
00:00:36,289 --> 00:00:37,701
I'm not even sure it was taken

17
00:00:37,701 --> 00:00:43,784
at the same moment as the bird's-eye view.

18
00:00:43,784 --> 00:00:45,993
In my lab, we develop tools

19
00:00:45,993 --> 00:00:47,757
to travel not only in space

20
00:00:47,757 --> 00:00:50,315
but also through time.

21
00:00:50,315 --> 00:00:52,185
The kind of question we're asking is

22
00:00:52,185 --> 00:00:53,578
Is it possible to build something

23
00:00:53,578 --> 00:00:55,756
like Google Maps of the past?

24
00:00:55,756 --> 00:00:59,066
Can I add a slider on top of Google Maps

25
00:00:59,066 --> 00:01:00,869
and just change the year,

26
00:01:00,869 --> 00:01:02,660
seeing how it was 100 years before,

27
00:01:02,660 --> 00:01:04,329
1,000 years before?

28
00:01:04,329 --> 00:01:06,452
Is that possible?

29
00:01:06,452 --> 00:01:08,704
Can I reconstruct social networks of the past?

30
00:01:08,704 --> 00:01:11,753
Can I make a Facebook of the Middle Ages?

31
00:01:11,753 --> 00:01:15,529
So, can I build time machines?

32
00:01:15,529 --> 00:01:18,094
Maybe we can just say, "No, it's not possible."

33
00:01:18,094 --> 00:01:21,904
Or, maybe, we can think of it from an information point of view.

34
00:01:21,904 --> 00:01:25,094
This is what I call the information mushroom.

35
00:01:25,094 --> 00:01:26,677
Vertically, you have the time.

36
00:01:26,677 --> 00:01:29,417
and horizontally, the amount of digital information available.

37
00:01:29,417 --> 00:01:32,899
Obviously, in the last 10 years, we have much information.

38
00:01:32,899 --> 00:01:36,447
And obviously the more we go in the past, the less information we have.

39
00:01:36,447 --> 00:01:38,765
If we want to build something like Google Maps of the past,

40
00:01:38,765 --> 00:01:40,259
or Facebook of the past,

41
00:01:40,259 --> 00:01:41,833
we need to enlarge this space,

42
00:01:41,833 --> 00:01:43,771
we need to make that like a rectangle.

43
00:01:43,771 --> 00:01:45,281
How do we do that?

44
00:01:45,281 --> 00:01:47,379
One way is digitization.

45
00:01:47,395 --> 00:01:49,174
There's a lot of material available --

46
00:01:49,190 --> 00:01:55,460
newspaper, printed books, thousands of printed books.

47
00:01:55,460 --> 00:01:57,228
I can digitize all these.

48
00:01:57,228 --> 00:01:59,965
I can extract information from these.

49
00:01:59,965 --> 00:02:03,508
Of course, the more you go in the past,
the less information you will have.

50
00:02:03,508 --> 00:02:06,154
So, it might not be enough.

51
00:02:06,154 --> 00:02:08,562
So, I can do what historians do.

52
00:02:08,562 --> 00:02:10,086
I can extrapolate.

53
00:02:10,086 --> 00:02:14,556
This is what we call, in computer science, simulation.

54
00:02:14,556 --> 00:02:16,307
If I take a log book,

55
00:02:16,307 --> 00:02:18,711
I can consider, it's not just a log book

56
00:02:18,711 --> 00:02:21,683
of a Venetian captain going to a particular journey.

57
00:02:21,683 --> 00:02:23,326
I can consider it is actually a log book

58
00:02:23,326 --> 00:02:25,908
which is representative of
many journeys of that period.

59
00:02:25,908 --> 00:02:28,153
I'm extrapolating.

60
00:02:28,153 --> 00:02:30,191
If I have a painting of a facade,

61
00:02:30,191 --> 00:02:32,942
I can consider it's not just that particular building,

62
00:02:32,942 --> 00:02:36,874
but probably it also shares the same grammar

63
00:02:36,874 --> 00:02:40,915
of buildings where we lost any information.

64
00:02:40,915 --> 00:02:43,773
So if we want to construct a time machine,

65
00:02:43,773 --> 00:02:45,112
we need two things.

66
00:02:45,112 --> 00:02:47,346
We need very large archives,

67
00:02:47,346 --> 00:02:50,088
and we need excellent specialists.

68
00:02:50,088 --> 00:02:51,962
The Venice Time Machine,

69
00:02:51,962 --> 00:02:53,767
the project I'm going to talk to you about,

70
00:02:53,767 --> 00:02:56,787
is a joint project between the EPFL

71
00:02:56,787 --> 00:02:59,765
and the University of Venice Ca'Foscari.

72
00:02:59,765 --> 00:03:01,930
There's something very peculiar about Venice,

73
00:03:01,930 --> 00:03:04,604
that its administration has been

74
00:03:04,604 --> 00:03:06,798
very, very bureaucratic.

75
00:03:06,798 --> 00:03:08,991
They've been keeping track of everything,

76
00:03:08,991 --> 00:03:11,906
almost like Google today.

77
00:03:11,906 --> 00:03:13,420
At the Archivio di Stato,

78
00:03:13,420 --> 00:03:15,184
you have 80 kilometers of archives

79
00:03:15,184 --> 00:03:17,193
documenting every aspect

80
00:03:17,193 --> 00:03:19,439
of the life of Venice over
more than 1,000 years.

81
00:03:19,439 --> 00:03:21,359
You have every boat that goes out,

82
00:03:21,359 --> 00:03:22,435
every boat that comes in.

83
00:03:22,435 --> 00:03:25,232
You have every change that was made in the city.

84
00:03:25,232 --> 00:03:28,523
This is all there.

85
00:03:28,523 --> 00:03:32,431
We are setting up a 10-year digitization program

86
00:03:32,431 --> 00:03:34,108
which has the objective of transforming

87
00:03:34,108 --> 00:03:35,492
this immense archive

88
00:03:35,492 --> 00:03:37,918
into a giant information system.

89
00:03:37,918 --> 00:03:39,775
The type of objective we want to reach

90
00:03:39,775 --> 00:03:44,501
is 450 books a day that can be digitized.

91
00:03:44,501 --> 00:03:46,748
Of course, when you digitize, that's not enough,

92
00:03:46,748 --> 00:03:48,035
because these documents,

93
00:03:48,035 --> 00:03:50,674
most of them are in Latin, in Tuscan,

94
00:03:50,689 --> 00:03:52,204
in Venetian dialect,

95
00:03:52,204 --> 00:03:53,879
so you need to transcribe them,

96
00:03:53,879 --> 00:03:55,560
to translate them in some cases,

97
00:03:55,560 --> 00:03:56,680
to index them,

98
00:03:56,680 --> 00:03:58,844
and this is obviously not easy.

99
00:03:58,844 --> 00:04:02,688
In particular, traditional optical
character recognition method

100
00:04:02,688 --> 00:04:04,112
that can be used for printed manuscripts,

101
00:04:04,112 --> 00:04:08,116
they do not work well on the handwritten document.

102
00:04:08,116 --> 00:04:10,246
So the solution is actually to take inspiration

103
00:04:10,246 --> 00:04:13,147
from another domain: speech recognition.

104
00:04:13,147 --> 00:04:15,202
This is a domain of something 
that seems impossible,

105
00:04:15,202 --> 00:04:17,739
which can actually be done,

106
00:04:17,739 --> 00:04:19,933
simply by putting additional constraints.

107
00:04:19,933 --> 00:04:21,519
If you have a very good model

108
00:04:21,519 --> 00:04:23,045
of a language which is used,

109
00:04:23,045 --> 00:04:25,131
if you have a very good model of a document,

110
00:04:25,131 --> 00:04:26,563
how well they are structured.

111
00:04:26,563 --> 00:04:27,916
And these are administrative documents.

112
00:04:27,931 --> 00:04:30,063
They are well structured in many cases.

113
00:04:30,063 --> 00:04:33,371
If you divide this huge archive into smaller subsets

114
00:04:33,371 --> 00:04:36,248
where a smaller subset
actually shares similar features,

115
00:04:36,248 --> 00:04:40,279
then there's a chance of success.

116
00:04:42,761 --> 00:04:45,196
If we reach that stage, then there's something else:

117
00:04:45,196 --> 00:04:48,718
we can extract from this document events.

118
00:04:48,718 --> 00:04:51,016
Actually probably 10 billion events

119
00:04:51,016 --> 00:04:52,947
can be extracted from this archive.

120
00:04:52,947 --> 00:04:54,671
And this giant information system

121
00:04:54,671 --> 00:04:56,487
can be searched in many ways.

122
00:04:56,487 --> 00:04:57,855
You can ask questions like,

123
00:04:57,855 --> 00:05:00,615
"Who lived in this palazzo in 1323?"

124
00:05:00,615 --> 00:05:02,837
"How much cost a sea bream at the Realto market

125
00:05:02,837 --> 00:05:04,561
in 1434?"

126
00:05:04,561 --> 00:05:06,021
"What was the salary

127
00:05:06,021 --> 00:05:08,066
of a glass maker in Murano

128
00:05:08,066 --> 00:05:09,472
maybe over a decade?"

129
00:05:09,472 --> 00:05:10,894
You can ask even bigger questions

130
00:05:10,894 --> 00:05:13,632
because it will be semantically coded.

131
00:05:13,632 --> 00:05:15,772
And then what you can do is put that in space,

132
00:05:15,772 --> 00:05:17,945
because much of this information is spatial.

133
00:05:17,945 --> 00:05:19,880
And from that, you can do things like

134
00:05:19,880 --> 00:05:21,993
reconstructing this extraordinary journey

135
00:05:21,993 --> 00:05:25,349
of that city that managed to
have a sustainable development

136
00:05:25,349 --> 00:05:27,475
over a thousand years,

137
00:05:27,475 --> 00:05:29,095
managing to have all the time

138
00:05:29,095 --> 00:05:31,956
a form of equilibrium with its environment.

139
00:05:31,956 --> 00:05:33,204
You can reconstruct that journey,

140
00:05:33,204 --> 00:05:36,100
visualize it in many different ways.

141
00:05:36,100 --> 00:05:38,799
But of course, you cannot understand 
Venice if you just look at the city.

142
00:05:38,799 --> 00:05:41,195
You have to put it in a larger European context.

143
00:05:41,195 --> 00:05:44,016
So the idea is also to document all the things

144
00:05:44,016 --> 00:05:46,439
that worked at the European level.

145
00:05:46,439 --> 00:05:48,403
We can reconstruct also the journey

146
00:05:48,403 --> 00:05:50,393
of the Venetian maritime empire,

147
00:05:50,393 --> 00:05:53,559
how it progressively controlled the Adriatic Sea,

148
00:05:53,559 --> 00:05:57,305
how it became the most powerful medieval empire

149
00:05:57,305 --> 00:05:58,866
of its time,

150
00:05:58,866 --> 00:06:01,038
controlling most of the sea routes

151
00:06:01,038 --> 00:06:03,971
from the east to the south.

152
00:06:05,305 --> 00:06:07,621
But you can even do other things,

153
00:06:07,621 --> 00:06:09,898
because in these maritime routes,

154
00:06:09,898 --> 00:06:11,873
there are regular patterns.

155
00:06:11,889 --> 00:06:14,382
You can go one step beyond

156
00:06:14,382 --> 00:06:16,502
and actually create a simulation system,

157
00:06:16,502 --> 00:06:19,317
create a Mediterranean simulator

158
00:06:19,317 --> 00:06:21,910
which is capable actually of reconstructing

159
00:06:21,910 --> 00:06:24,112
even the information we are missing,

160
00:06:24,112 --> 00:06:27,100
which would enable us to have 
questions you could ask

161
00:06:27,100 --> 00:06:30,088
like if you were using a route planner.

162
00:06:30,088 --> 00:06:33,159
"If I am in Corfu in June 1323

163
00:06:33,159 --> 00:06:35,685
and want to go to Constantinople,

164
00:06:35,685 --> 00:06:37,828
where can I take a boat?"

165
00:06:37,828 --> 00:06:39,195
Probably we can answer this question

166
00:06:39,195 --> 00:06:43,668
with one or two or three days' precision.

167
00:06:43,668 --> 00:06:45,275
"How much will it cost?"

168
00:06:45,275 --> 00:06:48,867
"What are the chance of encountering pirates?"

169
00:06:48,867 --> 00:06:50,678
Of course, you understand,

170
00:06:50,678 --> 00:06:53,287
the central scientific challenge
of a project like this one

171
00:06:53,287 --> 00:06:57,016
is qualifying, quantifying and representing

172
00:06:57,016 --> 00:07:00,346
uncertainty and inconsistency
at each step of this process.

173
00:07:00,346 --> 00:07:03,058
There are errors everywhere,

174
00:07:03,058 --> 00:07:05,547
errors in the document, it's
the wrong name of the captain,

175
00:07:05,547 --> 00:07:08,760
some of the boats never actually took to sea.

176
00:07:08,760 --> 00:07:13,617
There are errors in translation, interpretative biases,

177
00:07:13,624 --> 00:07:17,090
and on top of that, if you add algorithmic processes,

178
00:07:17,090 --> 00:07:20,039
you're going to have errors in recognition,

179
00:07:20,039 --> 00:07:22,000
errors in extraction,

180
00:07:22,000 --> 00:07:26,481
so you have very, very uncertain data.

181
00:07:26,481 --> 00:07:30,238
So how can we detect and
correct these inconsistencies?

182
00:07:30,238 --> 00:07:33,898
How can we represent that form of uncertainty?

183
00:07:33,898 --> 00:07:35,995
It's difficult. One thing you can do

184
00:07:35,995 --> 00:07:38,221
is document each step of the process,

185
00:07:38,221 --> 00:07:40,669
not only coding the historical information

186
00:07:40,669 --> 00:07:43,348
but what we call the meta-historical information,

187
00:07:43,348 --> 00:07:46,011
how is historical knowledge constructed,

188
00:07:46,011 --> 00:07:48,009
documenting each step.

189
00:07:48,009 --> 00:07:49,654
That will not guarantee that we actually converge

190
00:07:49,654 --> 00:07:52,104
toward a single story of Venice,

191
00:07:52,104 --> 00:07:54,242
but probably we can actually reconstruct

192
00:07:54,242 --> 00:07:57,290
a fully documented potential story of Venice.

193
00:07:57,290 --> 00:07:58,749
Maybe there's not a single map.

194
00:07:58,749 --> 00:08:00,869
Maybe there are several maps.

195
00:08:00,869 --> 00:08:03,085
The system should allow for that,

196
00:08:03,085 --> 00:08:05,944
because we have to deal with
a new form of uncertainty,

197
00:08:05,944 --> 00:08:10,585
which is really new for this type of giant databases.

198
00:08:10,585 --> 00:08:12,775
And how should we communicate

199
00:08:12,790 --> 00:08:16,769
this new research to a large audience?

200
00:08:16,769 --> 00:08:19,432
Again, Venice is extraordinary for that.

201
00:08:19,432 --> 00:08:21,603
With the millions of visitors that come every year,

202
00:08:21,603 --> 00:08:23,366
it's actually one of the best places

203
00:08:23,366 --> 00:08:26,354
to try to invent the museum of the future.

204
00:08:26,354 --> 00:08:29,658
Imagine, horizontally you see the reconstructed map

205
00:08:29,658 --> 00:08:30,944
of a given year,

206
00:08:30,944 --> 00:08:33,902
and vertically, you see the document

207
00:08:33,902 --> 00:08:35,413
that served the reconstruction,

208
00:08:35,413 --> 00:08:38,813
paintings, for instance.

209
00:08:38,813 --> 00:08:41,393
Imagine an immersive system that permits

210
00:08:41,393 --> 00:08:44,895
to go and dive and reconstruct
the Venice of a given year,

211
00:08:44,895 --> 00:08:47,610
some experience you could share within a group.

212
00:08:47,610 --> 00:08:49,856
On the contrary, imagine actually that you start

213
00:08:49,856 --> 00:08:52,063
from a document, a Venetian manuscript,

214
00:08:52,063 --> 00:08:55,112
and you show, actually, what
you can construct out of it,

215
00:08:55,112 --> 00:08:56,884
how it is decoded,

216
00:08:56,884 --> 00:08:59,299
how the context of that document can be recreated.

217
00:08:59,299 --> 00:09:01,184
This is an image from an exhibit

218
00:09:01,184 --> 00:09:03,460
which is currently conducted in Geneva

219
00:09:03,460 --> 00:09:05,814
with that type of system.

220
00:09:05,814 --> 00:09:07,989
So to conclude, we can say that

221
00:09:07,989 --> 00:09:11,068
research in the humanities is about to undergo

222
00:09:11,068 --> 00:09:12,870
an evolution which is maybe similar

223
00:09:12,870 --> 00:09:17,452
to what happened to life sciences 30 years ago.

224
00:09:17,452 --> 00:09:22,128
It's really a question of scale.

225
00:09:22,130 --> 00:09:25,433
We see projects which are

226
00:09:25,433 --> 00:09:29,276
much beyond any single research team can do,

227
00:09:29,276 --> 00:09:31,519
and this is really new for the humanities,

228
00:09:31,519 --> 00:09:35,388
which very often take the habit of working

229
00:09:35,388 --> 00:09:39,396
in small groups or only with a couple of researchers.

230
00:09:39,396 --> 00:09:41,514
When you visit the Archivio di Stato,

231
00:09:41,514 --> 00:09:44,336
you feel this is beyond what any single team can do,

232
00:09:44,336 --> 00:09:48,170
and that should be a joint and common effort.

233
00:09:48,170 --> 00:09:51,276
So what we must do for this paradigm shift

234
00:09:51,276 --> 00:09:53,178
is actually foster a new generation

235
00:09:53,178 --> 00:09:54,715
of "digital humanists"

236
00:09:54,715 --> 00:09:56,805
that are going to be ready for this shift.

237
00:09:56,805 --> 00:09:58,764
I thank you very much.

238
00:09:58,764 --> 00:10:02,764
(Applause)