1 / 54

CL vs NLP

CL vs NLP. Why “Computational Linguistics (CL)” rather than “Natural Language Processing” (NLP)? Computational Linguistics — Computers dealing with language — Modeling what people do Natural Language Processing —Applications on the computer side. Relation of CL to Other Disciplines.

gregr
Download Presentation

CL vs NLP

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CL vs NLP • Why “Computational Linguistics (CL)” rather than “Natural Language Processing” (NLP)? • Computational Linguistics • — Computers dealing with language • — Modeling what people do • Natural Language Processing • —Applications on the computer side

  2. Relation of CL to Other Disciplines Electrical Engineering (EE) (Optical Character Recognition) Artificial Intelligence (AI) (notions of rep, search, etc.) Linguistics (Syntax, Semantics, etc.) Machine Learning (particularly, probabilistic or statistic ML techniques) Psychology CL Philosophy of Language, Formal Logic Human Computer Interaction (HCI) Information Retrieval Theory of Computation

  3. A Sampling of “Other Disciplines” • Linguistics: formal grammars, abstract characterization of what is to be learned. • Computer Science: algorithms for efficient learning or online deployment of these systems in automata. • Engineering: stochastic techniques for characterizing regular patterns for learning and ambiguity resolution. • Psychology: Insights into what linguistic constructions are easy or difficult for people to learn or to use

  4. History: 1940-1950’s • Development of formal language theory (Chomsky, Kleene, Backus). • Formal characterization of classes of grammar (context-free, regular) • Association with relevant automata • Probability theory: language understanding as decoding through noisy channel (Shannon) • Use of information theoretic concepts like entropy to measure success of language models.

  5. 1957-1983 Symbolic vs. Stochastic • Symbolic • Use of formal grammars as basis for natural language processing and learning systems. (Chomsky, Harris) • Use of logic and logic based programming for characterizing syntactic or semantic inference (Kaplan, Kay, Pereira) • First toy natural language understanding and generation systems (Woods, Minsky, Schank, Winograd, Colmerauer) • Discourse Processing: Role of Intention, Focus (Grosz, Sidner, Hobbs) • Stochastic Modeling • Probabilistic methods for early speech recognition, OCR (Bledsoe and Browning, Jelinek, Black, Mercer)

  6. 1983-1993: Return of Empiricism • Use of stochastic techniques for part of speech tagging, parsing, word sense disambiguation, etc. • Comparison of stochastic, symbolic, more or less powerful models for language understanding and learning tasks.

  7. 1993-Present • Advances in software and hardware create NLP needs for information retrieval (web), machine translation, spelling and grammar checking, speech recognition and synthesis. • Stochastic and symbolic methods combine for real world applications.

  8. Language and Intelligence: Turing Test • Turing test: • machine, human, and human judge • Judge asks questions of computer and human. • Machine’s job is to act like a human, human’s job is to convince judge that he’s not the machine. • Machine judged “intelligent” if it can fool judge. • Judgement of “intelligence” linked to appropriate answers to questions from the system.

  9. ELIZA • Remarkably simple “Rogerian Psychologist” • Uses Pattern Matching to carry on limited form of conversation. • Seems to “Pass the Turing Test!” (McCorduck, 1979, pp. 225-226) • Eliza Demo: http://www.lpa.co.uk/pws_dem4.htm

  10. What’s involved in an “intelligent” Answer? Analysis: Decomposition of the signal (spoken or written) eventually into meaningful units. This involves …

  11. Speech/Character Recognition • Decomposition into words, segmentation of words into appropriate phones or letters • Requires knowledge of phonological patterns: • I’m enormously proud. • I mean to make you proud.

  12. Morphological Analysis • Inflectional • duck + s = [N duck] + [plural s] • duck + s = [V duck] + [3rd person s] • Derivational • kind, kindness • Spelling changes • drop, dropping • hide, hiding

  13. S NP VP I V NP OR: watch Subject Object I terrapin Det the watched det N the terrapin Syntactic Analysis • Associate constituent structure with string • Prepare for semantic interpretation

  14. Semantics • A way of representing meaning • Abstracts away from syntactic structure • Example: • First-Order Logic: watch(I,terrapin) • Can be: “I watched the terrapin” or “The terrapin was watched by me” • Real language is complex: • Who did I watch?

  15. Lexical Semantics The Terrapin, is who I watched. Watch the Terrapin is what I do best. *Terrapin is what I watched the I= experiencer Watch the Terrapin = predicate The Terrapin = patient

  16. Proposition Experiencer Predicate: Be (perc) I (1st pers, sg) pred patient saw the Terrapin Compositional Semantics • Association of parts of a proposition with semantic roles • Scoping

  17. Word-Governed Semantics • Any verb can add “able” to form an adjective. • I taught the class . The class is teachable • I rejected the idea. The idea is rejectable. • Association of particular words with specific semantic forms. • John (masculine) • The boys ( masculine, plural, human)

  18. Pragmatics • Real world knowledge, speaker intention, goal of utterance. • Related to sociology. • Example 1: • Could you turn in your assignments now (command) • Could you finish the homework? (question, command) • Example 2: • I couldn’t decide how to catch the crook. Then I decided to spy on the crook with binoculars. • To my surprise, I found out he had them too. Then I knew to just follow the crook with binoculars. [ the crook [with binoculars]] [ the crook] [ with binoculars]

  19. Discourse Analysis • Discourse: How propositions fit together in a conversation—multi-sentence processing. • Pronoun reference: The professor told the student to finish the assignment. He was pretty aggravated at how long it was taking to pass it in. • Multiple reference to same entity:George W. Bush, president of the U.S. • Relation between sentences:John hit the man. He had stolen his bicycle

  20. NLP Pipeline speech text Phonetic Analysis OCR/Tokenization Morphological analysis Syntactic analysis Semantic Interpretation Discourse Processing

  21. Relation to Machine Translation analysis input generation output Morphological analysis Morphological synthesis Syntactic analysis Syntactic realization Semantic Interpretation Lexical selection Interlingua

  22. Ambiguity I made her duck I made duckling for her I made the duckling belonging to her I created the duck she owns I forced her to lower her head By magic, I changed her into a duck

  23. Syntactic Disambiguation S S NP VP NP VP I V NP VP I V NP made her V made det N duck her duck • Structural ambiguity:

  24. Part of Speech Tagging and Word Sense Disambiguation • [verb Duck ] ! [noun Duck] is delicious for dinner • I went to the bank to deposit my check. I went to the bank to look out at the river. I went to the bank of windows and chose the one dealing with last names beginning with “d”.

  25. Resources forNLP Systems • Dictionary • Morphology and Spelling Rules • Grammar Rules • Semantic Interpretation Rules • Discourse Interpretation • Natural Language processing involves (1) learning or fashioning the rules for each component, (2) embedding the rules in the relevant automaton, (3) and using the automaton to efficiently process the input .

  26. Some NLP Applications • Machine Translation—Babelfish (Alta Vista): • Question Answering—Ask Jeeves (Ask Jeeves): • Language Summarization—MEAD (U. Michigan): • Spoken Language Recognition— EduSpeak (SRI): • Automatic Essay evaluation—E-Rater (ETS): • Information Retrieval and Extraction—NetOwl (SRA): http://babelfish.altavista.com/translate.dyn http://www.ask.com/ http://www.summarization.com/mead http://www.eduspeak.com/ http://www.ets.org/research/erater.html http://www.netowl.com/extractor_summary.html

  27. What is MT? • Definition: Translation from one natural language to another by means of a computerized system • Early failures • Later: varying degrees of success

  28. An Old Example The spirit is willing but the flesh is weak The vodka is good but the meat is rotten

  29. Machine Translation History • 1950’s: Intensive research activity in MT • 1960’s: Direct word-for-word replacement • 1966 (ALPAC): NRC Report on MT • Conclusion: MT no longer worthy of serious scientific investigation. • 1966-1975: `Recovery period’ • 1975-1985: Resurgence (Europe, Japan) • 1985-present: Resurgence (US) http://ourworld.compuserve.com/homepages/WJHutchins/MTS-93.htm.

  30. What happened between ALPAC and Now? • Need for MT and other NLP applications confirmed • Change in expectations • Computers have become faster, more powerful • WWW • Political state of the world • Maturation of Linguistics • Development of hybrid statistical/symbolic approaches

  31. Three MT Approaches: Direct, Transfer, Interlingual Interlingua Semantic Composition Semantic Decomposition Semantic Structure Semantic Structure Semantic Analysis Semantic Generation Semantic Transfer Syntactic Structure Syntactic Structure Syntactic Transfer Syntactic Analysis Syntactic Generation Word Structure Word Structure Direct Morphological Generation Morphological Analysis Target Text Source Text

  32. Examples of Three Approaches • Direct: • I checked his answers against those of the teacher → Yo comparé sus respuestas a las de la profesora • Rule: [check X against Y] → [comparar X a Y] • Transfer: • Ich habe ihn gesehen → I have seen him • Rule: [clause agt aux obj pred] → [clause agt aux pred obj] • Interlingual: • I like Mary→Mary me gusta a mí • Rep: [BeIdent (I [ATIdent (I, Mary)] Like+ingly)]

  33. MT Systems: 1964-1990 • Direct: GAT [Georgetown, 1964], TAUM-METEO [Colmerauer et al. 1971] • Transfer: GETA/ARIANE [Boitet, 1978]LMT [McCord, 1989], METAL [Thurmair, 1990], MiMo [Arnold & Sadler, 1990], … • Interlingual: MOPTRANS [Schank, 1974], KBMT [Nirenburg et al, 1992], UNITRAN [Dorr, 1990]

  34. Statistical MT and Hybrid Symbolic/Stats MT: 1990-Present Candide [Brown, 1990, 1992]; Halo/Nitrogen [Langkilde and Knight, 1998], [Yamada and Knight, 2002]; GHMT [Dorr and Habash, 2002]; DUSTer [Dorr et al. 2002]

  35. Direct MT: Pros and Cons • Pros • Fast • Simple • Inexpensive • Cons • Unreliable • Not powerful • Rule proliferation • Requires too much context • Major restructuring after lexical substitution

  36. Transfer MT: Pros and Cons • Pros • Don’t need to find language-neutral rep • No translation rules hidden in lexicon • Relatively fast • Cons • N2 sets of transfer rules: Difficult to extend • Proliferation of language-specific rules in lexicon and syntax • Cross-language generalizations lost

  37. Interlingual MT: Pros and Cons • Pros • Portable (avoids N2 problem) • Lexical rules and structural transformations stated more simply on normalized representation • Explanatory Adequacy • Cons • Difficult to deal with terms on primitive level: universals? • Must decompose and reassemble concepts • Useful information lost (paraphrase)

  38. Approximate IL Approach • Tap into richness of TL resources • Use some, but not all, components of IL representation • Generate multiple sentences that are statistically pared down

  39. Approximating IL: Handling Divergences • Primitives • Semantic Relations • Lexical Information

  40. Interlingual vs. Approximate IL • Interlingual MT: • primitives & relations • bi-directional lexicons • analysis: compose IL • generation: decompose IL • Approximate IL • hybrid symbolic/statistical design • overgeneration with statistical ranking • uses dependency rep input and structural expansion for “deeper” overgeneration

  41. [CAUSE GO] [CAUSE GO] GIVEV KICKV Agent Theme Agent Goal Goal MARY MARY JOHN JOHN KICKN Mapping from Input Dependency to English Dependency Tree Mary le dio patadas a John → Mary kicked John Knowledge Resources in English only: (LVD; Dorr, 2001).

  42. Statistical Extraction Mary kicked John . [0.670270 ] Mary gave a kick at John . [-2.175831] Mary gave the kick at John . [-3.969686] Mary gave an kick at John . [-4.489933] Mary gave a kick by John . [-4.803054] Mary gave a kick to John . [-5.045810] Mary gave a kick into John . [-5.810673] Mary gave a kick through John . [-5.836419] Mary gave a foot wound by John . [-6.041891] Mary gave John a foot wound . [-6.212851]

  43. Benefits of Approximate IL Approach • Explaining behaviors that appear to be statistical in nature • “Re-sourceability”: Re-use of already existing components for MT from new languages. • Application to monolingual alternations

  44. What Resources are Required? • Deep TL resources • Requires SL parser and tralex • TL resources are richer: LVD representations, CatVar database • Constrained overgeneration

  45. MT Challenges: Ambiguity • Syntactic AmbiguityI saw the man on the hill with the telescope • Lexical Ambiguity E: book S: libro, reservar • Semantic Ambiguity • Homography:ball(E) = pelota, baile(S) • Polysemy:kill(E), matar, acabar (S) • Semantic granularityesperar(S) = wait, expect, hope (E)be(E) = ser, estar(S)fish(E) = pez, pescado(S)

  46. How do we evaluate MT? • Human-based Metrics • Semantic Invariance • Pragmatic Invariance • Lexical Invariance • Structural Invariance • Spatial Invariance • Fluency • Accuracy • “Do you get it?” • Automatic Metrics: Bleu

  47. BiLingual Evaluation Understudy (BLEU —Papineni, 2001) • Automatic Technique, but …. • Requires the pre-existence of Human (Reference) Translations • Approach: • Produce corpus of high-quality human translations • Judge “closeness” numerically (word-error rate) • Compare n-gram matches between candidate translation and 1 or more reference translations http://www.research.ibm.com/people/k/kishore/RC22176.pdf

  48. Bleu Comparison Chinese-English Translation Example: Candidate 1: It is a guide to action which ensures that the military always obeys the commands of the party. Candidate 2: It is to insure the troops forever hearing the activity guidebook that party direct. Reference 1: It is a guide to action that ensures that the military will forever heed Party commands. Reference 2: It is the guiding principle which guarantees the military forces always being under the command of the Party. Reference 3: It is the practical guide for the army always to heed the directions of the party.

  49. How Do We Compute Bleu Scores? • Key Idea: A reference word should be considered exhausted after a matching candidate word is identified. • For each word compute: • (1) candidate word count • (2) maximum ref count • Add counts for each candidate word using the lower of the two numbers . • Divide by number of candidate words..

  50. Modified Unigram Precision: Candidate #1 It(1) is(1) a(1) guide(1) to(1) action(1) which(1) ensures(1) that(2) the(4) military(1) always(1) obeys(0) the commands(1) of(1) the party(1) Reference 1: It is a guide to action that ensures that the military will forever heed Party commands. Reference 2: It is the guiding principle which guarantees the military forces always being under the command of the Party. Reference 3: It is the practical guide for the army always to heed the directions of the party. What’s the answer?????? 17/18

More Related