Introduction to Natural Language Processing

1. Introduction to Natural Language Processing (Lecture for CS410 Text Information Systems) Jan 28, 2011 ChengXiang Zhai Department of Computer Science University of Illinois, Urbana-Champaign

2. Lecture Plan • What is NLP? • A brief history of NLP • The current state of the art • NLP and text management

3. What is NLP? Thai: …เรา เล่น ฟุตบอล … How can a computer make sense out of this string? - What are the basic units of meaning (words)? - What is the meaning of each word? - How are words related with each other? - What is the “combined meaning” of words? - What is the “meta-meaning”? (speech act) - Handling a large chunk of text - Making sense of everything Morphology Syntax Semantics Pragmatics Discourse Inference

4. Det Noun Aux Verb Det Noun Prep Det Noun Noun Phrase Noun Phrase Noun Phrase Complex Verb Prep Phrase Semantic analysis Verb Phrase Dog(d1). Boy(b1). Playground(p1). Chasing(d1,b1,p1). Verb Phrase + Sentence Scared(x) if Chasing(_,x,_). A person saying this may be reminding another person to get the dog back… Scared(b1) Inference Pragmatic analysis (speech act) An Example of NLP A dog is chasing a boy on the playground Lexical analysis (part-of-speech tagging) Syntactic analysis (Parsing)

5. If we can do this for all the sentences, then … BAD NEWS: Unfortunately, we can’t. General NLP = “AI-Complete”

6. NLP is Difficult!!!!!!! • Natural language is designed to make human communication efficient. As a result, • we omit a lot of “common sense” knowledge, which we assume the hearer/reader possesses • we keep a lot of ambiguities, which we assume the hearer/reader knows how to resolve • This makes EVERY step in NLP hard • Ambiguity is a “killer”! • Common sense reasoning is pre-required

7. Examples of Challenges • Word-level ambiguity: E.g., • “design” can be a noun or a verb (Ambiguous POS) • “root” has multiple meanings (Ambiguous sense) • Syntactic ambiguity: E.g., • “natural language processing” (Modification) • “A man saw a boy with a telescope.” (PP Attachment) • Anaphora resolution: “John persuaded Bill to buy a TV for himself.” (himself = John or Bill?) • Presupposition: “He has quit smoking.” implies that he smoked before.

8. Despite all the challenges, research in NLP has also made a lot of progress…

9. High-level History of NLP • Early enthusiasm (1950’s): Machine Translation • Too ambitious • Bar-Hillel report (1960) concluded that fully-automatic high-quality translation could not be accomplished without knowledge (Dictionary + Encyclopedia) • Less ambitious applications (late 1960’s & early 1970’s): Limited success, failed to scale up • Speech recognition • Dialogue (Eliza) • Inference and domain knowledge (SHRDLU=“block world”) • Real world evaluation (late 1970’s – now) • Story understanding (late 1970’s & early 1980’s) • Large scale evaluation of speech recognition, text retrieval, information extraction (1980 – now) • Statistical approaches enjoy more success (first in speech recognition & retrieval, later others) • Current trend: • Heavy use of machine learning techniques • Boundary between statistical and symbolic approaches is disappearing. • We need to use all the available knowledge • Application-driven NLP research (bioinformatics, Web, Question answering…) Deep understanding in limited domain Shallow understanding Knowledge representation Robust component techniques Stat. language models Learning-based NLP Applications

10. The State of the Art A dog is chasing a boy on the playground POS Tagging: 97% Det Noun Aux Verb Det Noun Prep Det Noun Noun Phrase Noun Phrase Noun Phrase Complex Verb Prep Phrase Verb Phrase Parsing: partial >90%(?) Semantics: some aspects - Entity/relation extraction - Word sense disambiguation - Anaphora resolution Verb Phrase Sentence Speech act analysis: ??? Inference: ???

11. This is a new sentence Det Aux Det Adj N “This is a new sentence” Method 1: Independent assignment Most common tag This is a new sentence Det Det Det Det Det … … Det Aux Det Adj N … … V2 V2 V2 V2 V2 Consider all possibilities, and pick the one with the highest probability Method 2: Partial dependency Technique Showcase: POS Tagging Training data (Annotated text) This sentence serves as an example of Det N V1 P Det N P annotated text… V2 N POS Tagger w1=“this”, w2=“is”, …. t1=Det, t2=Det, …,

12. Probability of this tree=0.000015 1.0 0.3 0.4 0.3 … … 1.0 0.01 0.003 … … roller skates Technique Showcase: Parsing S S NP VP NP  Det BNP NP  BNP NP NP PP BNP N VP  V VP  Aux V NP VP  VP PP PP  P NP V  chasing Aux is N  dog N  boy N playground Det the Det a P  on NP VP Det BNP VP PP Grammar A N Aux V NP P NP chasing on dog is a boy the playground Generate S Choose a tree with highest prob…. NP VP Det NP BNP Aux V Lexicon PP A NP N is chasing NP P dog a boy on the playground Can also be treated as a classification/decision problem…

13. Semantic Analysis Techniques • Only successful for VERY limited domain or for SOME aspect of semantics • E.g., • Entity extraction (e.g., recognizing a person’s name): Use rules and/or machine learning • Word sense disambiguation: addressed as a classification problem with supervised learning • Sentiment tagging • Anaphora resolution … In general, exploiting machine learning and statistical language models…

14. What We Can’t Do • 100% POS tagging • “He turned off the highway.” vs “He turned off the fan.” • General complete parsing • “A man saw a boy with a telescope.” • Deep semantic analysis • Will we ever be able to precisely define the meaning of “own” in “John owns a restaurant.”? Robust & general NLP tends to be “shallow”, while “deep” understanding doesn’t scale up …

15. Our focus Major NLP Applications • Speech recognition: e.g., Auto telephone call routing • Text management • Text retrieval/filtering • Text classification • Text summarization • Text mining • Query answering • Language tutoring • Spelling/grammar correction • Machine translation • Cross-language retrieval • Restricted natural language • Natural language user interface

16. NLP & Text Management Better NLP => Better Text Management Bad NLP => Bad Text Management? Robust, shallow NLP tends to be more useful than deep, but fragile NLP. Errors in NLP can hurt text management performance…

17. How Much NLP is Really Needed? “Easier” & More “workarounds” Tasks Dependency on NLP Classification/ Retrieval Summarization/ Extraction/ Mining Translation/ Dialogue Question Answering

18. How does it work? • Heuristic rules based on • Keyword matching! E.g., • I remember X => • Do you often think of X? always => Can you think of a specific example? It keeps the dialogue going on, but NEVER makes any claim! A breakdown example: Person : Failure is the mother of success. ELIZA : Tell me more about your family Workaround Example I: ELIZA ELIZA plays the role of a therapist Person : Men are all alike. ELIZA : In what way? Person : They're always bugging us about something or other. ELIZA : Can you think of a specific example? Person : Well, my boyfriend made me come here. ELIZA : Your boyfriend made you come here? Person : He says I'm depressed much of the time. ELIZA : I am sorry to hear that you are depressed. Person : It's true. I am unhappy. ELIZA : Do you think coming here will help you not to be unhappy? Person : I need some help, that much seems certain. ELIZA : What would it mean to you if you got some help? Person : Perhaps I could learn to get along with my mother. ELIZA : Tell me more about your family No NLP, but useful. Perhaps we should call this NLP? Statistical NLP often has a similar flavor with “SOFT” rules LEARNED from data

19. All these intuitions are captured through a probabilistic model Chinese Words(C) English Words (E) Translator English Translation English Speaker Noisy Channel P(E|C)=? P(E) P(C|E) Workaround Example II: Statistical Translation • Learn how to translate Chinese to English from many example translations • Intuitions: • If we have seen all possible translations, then we simply lookup • If we have seen a similar translation, then we can adapt • If we haven’t seen any example that’s similar, we try to generalize what we’ve seen

20. So, what NLP techniques are most useful for text management? Statistical NLP in general, and statistical language models in particular The need for high robustness and efficiency implies the dominant use of simple models (i.e., unigram models)

21. What You Should Know • NLP is the basis for text management • Better NLP enables better text management • Better NLP is necessary for sophisticated tasks • But • Bad NLP doesn’t mean bad text management • There are often “workarounds” for a task • Inaccurate NLP can even hurt the performance of a task • The most effective NLP techniques are often statistical with the help of linguistic knowledge • The challenge is to bridge the gap between NLP and applications