Title: Fractal Composition of Meaning: Toward a Collage Theorem for Language
1Fractal Composition of MeaningToward a Collage
Theorem for Language
- Simon D. Levy
- Department of Computer Science
- Washington and Lee University
- Lexington, VA 24450
- http//www.cs.wlu.edu/levy
2Part I Self-Similarity
3(No Transcript)
4(No Transcript)
5(No Transcript)
6(No Transcript)
7(No Transcript)
8(No Transcript)
9(No Transcript)
10... But I know, too,
11 That
12 the blackbird is involved in
13 what
14... But I know, too, That the blackbird is
involved In what Wallace Stevens
I know.
15Part II A Little Math
16Iterated Function Systems
- IFS Another way to make a fractal
- Start with an arbitrary initial image
- Apply a set of contractive affine transforms
-
- Repeat until image no longer changes
- E.g., Sierpinski Triangle...
17Sierpinski Triangle
I.e., three half-size copies, one in each of
three corners of 0,1 2
18Sierpinski Triangle 0 Iterations
19Sierpinski Triangle 1 Iteration
20Sierpinski Triangle 2 Iterations
21Sierpinski Triangle 3 Iterations
22Sierpinski Triangle 4 Iterations
23Sierpinski Triangle 5 Iterations
24Sierpinski Triangle 6 Iterations
25Sierpinski Triangle 7 Iterations
26Sierpinski Triangle New Initial Image
27Sierpinski Triangle
28Sierpinski Triangle
29Sierpinski Triangle
30Sierpinski Triangle
31Sierpinski Triangle
32Sierpinski Triangle
33Sierpinski Triangle
34IFS Fractals in Nature
35Fractal Image Compression
- Doesn't matter what image we start with
- All information needed to represent final
target image is contained in transforms
- Instead of storing millions of pixels, determine
transforms for target image, and store them - How to determine transforms?
36The Collage Theorem
- Let
- is the attractor or fixed
point of - Collage Theorem (Barnsley 1988) Given
arbitrary target image , transforms encoding
are s.t. - Use various practical methods to find
37Practical Fractal Image Compression
- Most real-world images are only partially
self-similar - Arbitrary images can be partitioned into
tiles, each associated with a transform. - Compression algorithm computes and stores
locations and transforms of tiles
38Practical Fractal Image Compression
39Practical Fractal Image Compression
40Part III Unification
41The Two Cultures
Semantic Relations
Discrete Symbols
Grammar Rules
Logic
Linguistics
AI
Metric Spaces
Graph Structures
Continuous Vectors
Dynamical Systems
Electrical Engineering
Images
Continuous Transforms
Chaos
42Meanings as Vectors
You shall know a word by the company it keeps
J. R. Firth
- Vector representation of a word encodes
co-occurrence with other words - Latent Semantic Analysis (Indexing) Singular
Value Decomposition of co-occurrence matrix on
text 300-dimensional vectors Landauer, Dumais,
Kintsch
43Meanings as Vectors
- Self-Organizing Maps Collapse high-dimensional
descriptions (binary features or real-val
vectors) into 2-D Kohonen - Simple Recurrent Networks Hidden-variable
temporal model predicting next word based on
current 150-D vectors Elman
44Meanings as Vectors
Fred says the woman arrived. The woman says fred
arrived. Fred loves the woman. The woman loves
fred. The woman arrived. Fred arrived.
45Composing Meaningful Vectors
the woman.
46Composing Meaningful Vectors
loves the woman.
47Composing Meaningful Vectors
Fred loves the woman.
48Part IV Conclusions
49Advantages of Vector Representations
- Meaning as a gradient phenomenon (semantic
spaces vector spaces) - Can represent all transforms with a single
hidden-variable non-linear equation (grammar) - Gradient-descent methods as learning model
- Principled, biologically plausible alternative
to Words and Rules approach Chomsky, Pinker,
Fodor
50A Collage Theorem for Language
51A Collage Conjecture for Language
52A Collage Conjecture for Language
53A Collage Hypothesis for Language
54A Collage Hypothesis for Language
55A Collage S.W.A.G. for Language
- Words/meanings are co-occurrence vectors.
- Compositions of meanings are transients to
words. - Correct set of transients is one for which
word vectors form a subset of the attractor.