From 86325089bc71991311af82650ae39d8c47982236 Mon Sep 17 00:00:00 2001 From: Dimitri Lozeve Date: Mon, 3 Feb 2020 18:49:59 +0100 Subject: [PATCH] Update draft on symbol grounding --- bib/bibliography.bib | 32 +++++++++++++ posts/symbol-grounding.org | 97 ++++++++++++++++++++++++++++++-------- 2 files changed, 109 insertions(+), 20 deletions(-) diff --git a/bib/bibliography.bib b/bib/bibliography.bib index 5fde888..5b490f8 100644 --- a/bib/bibliography.bib +++ b/bib/bibliography.bib @@ -47,3 +47,35 @@ DATE_ADDED = {Thu Nov 7 14:36:52 2019}, } +@Book{marcus2019_reboot_ai, + author = {Marcus, Gary}, + title = {Rebooting AI : building artificial intelligence we + can trust}, + year = 2019, + publisher = {Pantheon Books}, + address = {New York}, + isbn = 9781524748258, +} + +@article{miller2003_cognit_revol, + author = {George A Miller}, + title = {The Cognitive Revolution: a Historical Perspective}, + journal = {Trends in Cognitive Sciences}, + volume = {7}, + number = {3}, + pages = {141-144}, + year = {2003}, + doi = {10.1016/s1364-6613(03)00029-9}, + url = {https://doi.org/10.1016/s1364-6613(03)00029-9}, + DATE_ADDED = {Thu Dec 26 11:09:31 2019}, +} + +@book{kahneman2011_think_fast_slow, + author = {Kahneman, Daniel}, + title = {Thinking, Fast and Slow}, + year = 2011, + publisher = {Farrar, Straus and Giroux}, + url = {https://books.google.fr/books?id=SHvzzuCnuv8C}, + isbn = 9780374275631, + lccn = 2012533187, +} diff --git a/posts/symbol-grounding.org b/posts/symbol-grounding.org index 590ebc0..9f5432b 100644 --- a/posts/symbol-grounding.org +++ b/posts/symbol-grounding.org @@ -3,19 +3,19 @@ title: "Reading Notes: \"The Symbol Grounding Problem\", Stevan Harnad" date: 2020-02-02 --- -cite:harnad1990_symbol_groun_probl defined the /symbol grounding -problem/, which is one of the most influential issues in natural -language problems since the 1980s. The issue is to determine how a -formal language system, consisting in simple symbols, can be imbued -with any /meaning/. +cite:harnad1990_symbol_groun_probl [[https://eprints.soton.ac.uk/250382/1/symgro.pdf][(PDF version)]] defined the /symbol +grounding problem/, which is one of the most influential issues in +natural language problems since the 1980s. The issue is to determine +how a formal language system, consisting in simple symbols, can be +imbued with any /meaning/. From the abstract: #+begin_quote -How can the semantic interpretation of a formal symbol system can be -made /intrinsic/ to the system, rather than just parasitic on the -meanings in our heads? How can the meanings of the meaningless symbol -tokens, manipulated solely on the basis of their (arbitrary) shapes, -can be grounded in anything but other meaningless symbols? +How can the semantic interpretation of a formal symbol system be made +/intrinsic/ to the system, rather than just parasitic on the meanings +in our heads? How can the meanings of the meaningless symbol tokens, +manipulated solely on the basis of their (arbitrary) shapes, be +grounded in anything but other meaningless symbols? #+end_quote In this landmark paper, Harnad makes the issue explicit, in its @@ -25,24 +25,81 @@ combination of symbolic and connectionist properties. The problem itself is still highly relevant to today's NLP advances, where the issue of extracting /meaning/ is still not solved. -# cf Gary Marcus, /Rebooting AI/, and post on /The Gradient/ - * What is the symbol grounding problem? ** Context: cognitivism, symbolism, connectionism -/Cognitivism/ is the general framework in which all experimental -psychology takes place. It replaced old-fashioned /behaviorism/, -replacing it by an empirical science allowing to question the inner -workings of brains and minds. +/Behaviourism/ was the dominant framework of experimental psychology in +the first half of the 20th century. It grounded psychology firmly in +an empirical setting, arguing that mental events are not observable, +and that only external behaviour can be studied +citep:miller2003_cognit_revol. -Behaviorism restrained scientific inquiries to external behavior, -explicitly forbidding to make theories about what goes on inside the -mind. Cognitivism allowed the scientist to make hypotheses about +In the 1950s, new theories, in particular Chomsky's theories in +linguistics, started to question this approach and highlighted its +limitations. /Cognitivism/ arose as a way to take into account +internal mental states. It allowed scientists to make hypotheses about unobservable phenomenons, provided they made predictions testable in an experimental setting. -"Meaning" is one such unobservable phenomenon. +Harnad defines a /symbol system/ as a set of arbitrary token with +explicit rules (also in the form of tokens or strings of tokens) to +combine them. Note that the set of rules should be explicit and not +defined as posteriori, because nearly every phenomenon can be +interpreted as following a set of rules. + +An additional (and most relevant for us) property of symbol systems is +that they are /semantically interpretable/: we can associate a meaning +in a systematic fashion to every token or string of tokens. + +This exposes /symbolism/, i.e. the view that cognition is a symbolic +system. The alternative view, /connectionism/, has its root in +biological models of the brain, and posits that the network of +connections in the brain is what defines cognition, without any formal +symbol system. + +#+begin_quote +According to connectionism, cognition is not symbol manipulation but +dynamic patterns of activity in a multilayered network of nodes or +units with weighted positive and negative +interconnections. citep:harnad1990_symbol_groun_probl +#+end_quote + +One common criticism of connectionism is that it does not meet the +compositionality criterion. Moreover, we cannot give a semantic +interpretation of connectionist patterns in a systematic way as we can +in symbolic systems. This issue was recently raised again by Gary +Marcus in his recent book /Rebooting AI/ +citep:marcus2019_reboot_ai. Human cognition makes extensive use of +internal representations. Chomsky's theories on the existence of a +"universal grammar" is a good example of such internal structure for +linguistics. These cognitive representations seem to be highly +structured (as demonstrated by the work of Kahneman and Tversky +citep:kahneman2011_think_fast_slow), and compositional. (See also his +[[https://thegradient.pub/an-epidemic-of-ai-misinformation/][recent article]] in /The Gradient/.) + +#+CAPTION: Connectionism versus symbol systems (Taken from cite:harnad1990_symbol_groun_probl.) +|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| *Strengths of connectionism:* | +| 1) Nonsymbolic Function: As long as it does not aspire to be a symbol system, a connectionist network has the advantage of not being subject to the symbol grounding problem. | +| 2) Generality: Connectionism applies the same small family of algorithms to many problems, whereas symbolism, being a methodology rather than an algorithm, relies on endless problem-specific symbolic rules. | +| 3) "Neurosimilitude": Connectionist architecture seems more brain-like than a Turing machine or a digital computer. | +| 4) Pattern Learning: Connectionist networks are especially suited to the learning of patterns from data. | +|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| *Weaknesses if connectionism:* | +| 1) Nonsymbolic Function: Connectionist networks, because they are not symbol systems, do not have the systematic semantic properties that many cognitive phenomena appear to have. | +| 2) Generality: Not every problem amounts to pattern learning. Some cognitive tasks may call for problem-specific rules, symbol manipulation, and standard computation. | +| 3) "Neurosimilitude": Connectionism's brain-likeness may be superficial and may (like toy models) camoflauge deeper performance limitations. | +|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| *Strengths of symbol systems:* | +| 1) Symbolic Function: Symbols have the computing power of Turing Machines and the systematic properties of a formal syntax that is semantically interpretable. | +| 2) Generality: All computable functions (including all cognitive functions) are equivalent to a computational state in a Turing Machine. | +| 3) Practical Successes: Symbol systems' ability to generate intelligent behavior is demonstrated by the successes of Artificial Intelligence. | +|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| *Weaknesses of symbol systems:* | +| 1) Symbolic Function: Symbol systems are subject to the symbol grounding problem. | +| 2) Generality: Turing power is too general. The solutions to AI's many toy problems do not give rise to common principles of cognition but to a vast variety of ad hoc symbolic strategies. | +|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| ** Exposing the issue: thought experiments