* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download ppt - UTRGV Faculty Web
Survey
Document related concepts
Transcript
Artificial intelligence and language Emmett Tomai University of Texas – Pan American What is Artificial Intelligence? Generally, the study of computation as a model of human-like thought ◦ The human mind is our best exemplar of an artifact capable of intelligent thought Pattern recognition Logical reasoning Problem solving Planning Learning Language Social interaction Creativity Goals and questions AI is a broad field, with many goals, approaches, assumptions and unresolved questions ◦ For some, the goal is to create an artificial mind ◦ For others, to discover a formal model of thought ◦ Others, to build machines (programs) that perform difficult human-like tasks Is computation sufficient to model human mental processes? How do those processes differ from existing algorithms? A bit of history AI was established as a field in 1956 at a research conference Early work was largely symbolic and deductive ◦ Concepts represented as symbols in a formal logical system ◦ Reasoning carried out through step-by-step deduction, attempting to mirror human processes Logical problem solving Many logical problems reduce to search, trying to find an optimal path among many possibilities ◦ Theorem proving ◦ Constraint satisfaction (flight planning, logistics problems) ◦ Checkers, chess, go, etc. However, complete logical search has serious problems with combinatoric explosion The Traveling Salesman Consider a salesman who wants to visit a bunch of small towns ◦ He has a list of distances between pairs of towns ◦ How should he figure out what order to visit them in? Can be solved by straightforward search ◦ How long do you think it would take you to figure out the best path for 25 towns? The Traveling Salesman Consider a salesman who wants to visit a bunch of small towns ◦ He has a list of distances between pairs of towns ◦ How should he figure out what order to visit them in? Finding the answer by straightforward search has complexity O(n!) ◦ So it would take a 2GHz computer around a billion years ◦ Some more clever solutions are O(2n) So how do people do it? Unlike complete logical formalisms, people solve problems quickly and easily using approximate methods ◦ We don’t prove the best solution, we come up with reasonable solutions (and quickly) ◦ We use poorly understood mechanisms like intuition, experience and creative thinking Modern AI is largely concerned with numerous approaches to bridge that gap Successes Mechanical self-diagnosis ◦ Used in autonomous spacecraft Expert systems ◦ Aide humans in identifying and solving known problems Deep blue, etc. ◦ Far better than the average human chess player, can even beat the best humans Google ◦ Uses AI language processing techniques for search Learn more about AI The Association for the Advancement of Artificial Intelligence (AAAI) ◦ The biggest, general society for AI research AI Topics at AAAI ◦ Great resource ◦ Seminal references for all major sub-fields of AI ◦ http://www.aaai.org/AITopics/pmwiki/pmwiki.php/AIT opics/HomePage ◦ (click on “Browse Topics”) Language understanding and AI Why would you want a computer to be competent at natural language (e.g. English, Spanish, etc.) ◦ ◦ ◦ ◦ ◦ ◦ ◦ Machine translation Intelligent tutoring systems Information retrieval (search engines) Question answering systems Information management (emails, blogs, news, etc.) Speech recognition Storytelling tools (generation, editing, evaluation, etc.) Bottom line: people use language to do a lot of things Language understanding and AI People have been studying language for a long time ◦ Literature, philosophy, linguistics ◦ Anthropology, psychology This has resulted in common levels of analysis ◦ ◦ ◦ ◦ ◦ Morphology: how words are constructed Lexicon: the words that are available in a language Syntax: structural relationships between words Semantics: the meaning or a word of combination of words Discourse: how meaning evolves over time in a monologue or dialogue ◦ Pragmatics: the purpose behind an utterance, how language is used ◦ World knowledge: facts about the world, common sense Language understanding and AI Early work (1950s) in machine translation assumed that translation was a matter of lexicon (changing the words) and syntax (changing the order) That proved far too simplistic: ◦ hydraulic ram = water sheep ◦ out of sight, out of mind = blind, crazy ◦ The spirit is willing but the flesh is weak. = The vodka is good but the meat is rotten. Language understanding and AI Chomsky (1957) provided a robust linguistic theory that was specific enough to inform a computational model Montague (1970) presented a formal, logical grammar casting syntax and semantics as a precise mathematical system male( he ) studies( he, linguistics ) … Language understanding and AI Numerous problems remain, starting with ambiguity ◦ There is often more than one syntactically correct parse: ◦ “Time flies like an arrow.” What’s the verb? ◦ “I saw the Grand Canyon flying to New York.” Who or what was flying? ◦ “I saw the man on the hill with the telescope.” Who was on the hill? Where was the telescope? This creates the same problem of combinatorial explosion as the traveling salesman problem Worse, real language is often syntactically incorrect Language understanding and AI Syntax alone isn’t enough to understand language, you need semantics, pragmatics and world knowledge ◦ How did you know the Grand Canyon wasn’t the one flying? ◦ Unfortunately, each of those bring in their own ambiguities and difficulties Language understanding and AI Lexical ambiguity ◦ I walked to the bank ... of the river. to get money. ◦ The bug in the room ... was planted by spies. flew out the window. ◦ I work for John Hancock ... and he is a good boss. which is a good company. Language understanding and AI Co-reference resolution ◦ ◦ ◦ ◦ ◦ ◦ President John F. Kennedy was assassinated. The president was shot yesterday. Relatives said that John was a good father. JFK was the youngest president in history. His family will bury him tomorrow. Friends of the Massachusetts native will hold a candlelight service in Mr. Kennedy’s home town. Language understanding and AI Pragmatics ◦ Mostly studied in conversational dialogue, but applies to any linguistic communication ◦ Rules of Conversation Can you tell me what time it is? 4:30. Could I please have the salt? <passes the salt> What platform does the 5:00 train leave from? It already left. ◦ Speech Acts I bet you $50 that the Jazz will win. You’re on. You’re fired! Language understanding and AI World Knowledge ◦ John went to the diner. He ordered a steak. He left a tip and went home. ◦ John wanted to commit suicide. He got a rope. Language understanding and AI A very hard problem, with a big potential payoff All the levels of analysis (lexical, syntactic, etc.) must work together in understanding ◦ But this leads to seemingly insurmountable complexity Many approaches being pursued ◦ The same as for AI in general, trying to bridge the gap between explosive complexity in the formal system and the ease with which people do it every day Knowledge is power Problem: people know a lot of things ◦ Common sense reasoning (where the gap is huge) seems to involve using that knowledge ◦ Understanding the pragmatics of language requires being able to reason about the situation surrounding what is being said Solutions? ◦ Build huge knowledge bases filled with common sense information that people might have Experience is the best teacher Problem: part of what people know is a huge number of experiences ◦ We remember prior events and apply them to the current situation ◦ We can even adapt similar but not identical situations and ideas to understand new situations and ideas Solutions? ◦ Case-based reasoning, storing logical representations of prior events ◦ Analogical reasoning, being reminded of similar things and appreciating how they compare and contrast Learning is fundamental Problem: people learn as they go ◦ We continue to adapt and expand our knowledge and capabilities ◦ It’s not clear what we start with and what we learn ◦ We don’t do the same stupid thing twice Solutions? ◦ Perhaps this is the answer to the previous two problems ◦ Many researchers think that a legitimate AI must involve learning, otherwise you’re just tweaking it to work on specific problems Reactive approaches Problem: something as simple as an ant or a fruit fly is capable of amazing navigation ◦ Our models of intelligence require massive computing power to simulate a fruit fly ◦ Modern robots have trouble crossing the room without crashing into things Solutions? ◦ Reactive architectures concentrate on doing simple operations really fast and really well Put enough of those together and maybe we’ll get intelligence ◦ It may not scale up to writing poetry, but at least it can avoid running into walls The statistical revolution Problem: formal, logical systems are fragile and struggle with environments far less complex than reality ◦ Can these really scale up to working in the real world with ambiguity, vagueness and incomplete knowledge? ◦ With something as “inherent” as language, are we really reasoning about each sentence or are we relying on more subconscious, fast-acting mechanisms? Solutions? ◦ Most NL work in the last two decades has focused on statistical methods The statistical revolution Statistical methods use machine learning algorithms to fit a model to the data ◦ Given 1000s of training examples, a statistical parser can achieve robust, high-performance results on similar text Effective on parsing, named entity extraction, noun-noun coreference resolution, semantic role labeling ◦ However, since it relies entirely on consistent patterns, a parser trained on one type of text (say the Wall Street Journal) performs poorly on another (say a textbook, novel or blog) Worse, this approach hasn’t been shown to scale very far beyond simple syntactic features Learning semantics Context constrains ambiguity ◦ Filters out possible meanings that don’t make sense TRIPS (Allen et al) ◦ The Rochester Interactive Planning System ◦ Collaborative planning between human and AI ◦ Shared goal provides context Can reason about what the person might mean Enables impressive speech understanding Learning requires constrained examples ◦ Utterances… ◦ …combined with an appropriate situation (context) Learning semantics for…? Virtual spaces provide flexible constraint ◦ There are only so many moves in checkers ◦ Only so many things you could try to do Constraint enables planning, problem-solving ◦ AI systems can reason about moves Can that constraint enable learning language? Learning semantics in games You are playing checkers ◦ You already know how to play ◦ Someone is giving you advice in Chinese ◦ Could you learn some Chinese that way? Learning semantics in games You are playing checkers ◦ You already know how to play ◦ Someone is giving you advice in Chinese ◦ Could you learn some Chinese that way? Assume that they know what they’re talking about ◦ Hypothesize mappings Words to items, actions in the game Phrases to reasonable moves they could be suggesting ◦ Test hypotheses as the game goes on Learning semantics in games You are playing mahjongg ◦ You don’t know how to play ◦ Someone is giving you advice in Chinese ◦ Could you learn some Chinese, and mahjongg at the same time? Learning semantics in games You are playing mahjongg ◦ You don’t know how to play ◦ Someone is giving you advice in Chinese ◦ Could you learn some Chinese, and mahjongg at the same time? Assume that they know what they’re talking about ◦ Hypothesize mappings for words, phrases ◦ Test hypotheses as the game goes on Much harder since you can’t filter out bad/nonsensical moves Have to play the game out to see what moves were good Requires a lot of patience and methodical testing Learning semantics in games Interactive learning would be faster ◦ Particularly with positive/negative feedback Knowledge helps ◦ Syntax, lexical categories, other widely available knowledge ◦ The more you know about games in general, the fewer options you’ll have to try Bootstrapping ◦ Start with very simple goals to start language learning ◦ Build up to more complex goals Planning in real-time strategy games Lots of recent work on planning in RTS games ◦ ◦ ◦ ◦ Not as neat and clean as classic games (chess, etc) Require real-time decisions, uncertainty, heuristics Lots of player and strategy analysis available Still a limited environment compared to reality Learning semantics in a RTS game Given specific goals and varied instructions to reach those goals, can an AI learn English semantics while learning to play an RTS game? How can you tell if it does? ◦ Evaluating language learning is hard and subjective ◦ Evaluating performance is easy Do the instructions help the AI learn to play better, faster? Once some language has been learned, can it go on to learn another game goal faster? Project details Spring – Summer 2011 StarCraft: Brood War ◦ AI player using BroodWar API (BWAPI) C++ dll Event-driven programming Expose game info, unit commands Most likely bridge to a higher-level language (python, lisp, java) ◦ Research existing dynamic planning agents ◦ Implement a planning agent in-game ◦ Test ability to plan and reach simple in-game goals Funded by a UTPA Faculty Research Council grant for the summer RA position Additional projects Adaptive narrative in shared, virtual worlds ◦ Many dynamic virtual world simulations Physics, economics, politics, etc. ◦ Narrative presentation is largely static Cut-scenes, quest text, dialogue trees, etc. ◦ How can we use AI techniques to create and present narrative that adapts to a dynamic, interactive environment? Current project ◦ Building up shared world infrastructure Shared interactions in a persistent, physically-based world ◦ Using publically available tools, libraries, engines, etc. Additional projects Simulating dramatic social interaction ◦ Physical interactions have been well simulated Physics-based movement and collision Combat abstractions ◦ Social interactions are less well explored Formal diplomacy (lacks emotions, personal relationships) Bargaining (also abstract) Relationship models (Fable, The Sims) Emergent story, independent of narrative/dramatic arcs Curiosity-driven, lacking communicative goals