Introduction to Computational Linguistics

Introduction to Computational Linguistics Eleni Miltsakaki AUTH Spring 2006-Lecture 1 1 Lets introduce ourselves Course: Introduction to Computational Linguistics (Ling 2-342) Meeting times: Monday 11:00-14:00 Meeting place: here

Prof: Eleni Miltsakaki BA Aristotle University -- English & American Lang. & Lit. MA University of Essex, UK -- Applied Linguistics PhD University of Pennsylvania, USA -- Theoretical and Computational Linguistics Students: ? 2 What is Computational Linguistics? A discipline between Linguistics and Computer Science

Concerned with the computational aspects of human language processing Has theoretical and applied components 3 Theoretical CL Formal theories about the linguistic knowledge that a human needs for generating and understanding language Simulation of aspects of the human language faculty and their implementation as computer programs

Overlaps and collaborates with Theoretical Linguistics, Computer Science, Psycholinguistics 4 Applied CL Focuses on the practical outcome of modeling human language use aka language engineering or human language technology Existing CL systems are far from achieving human ability but there are numerous possible

and useful applications Question/answering, summarization, translation, computer agents, educational applications etc 5 Why is language so difficult for a computer? AMBIGUITY! Natural languages are massively ambiguous at all levels of processing (but humans dont even notice)

To resolve ambiguity, humans employ not only a detailed knowledge of the language -- sounds, phonological rules, grammar, lexicon etc -- but also: Detailed knowledge of the world (e.g. knowing that apples can have bruises but not smiles, or that snow falls but London does not). The ability to follow a 'story', by connecting up sentences to form a continuous whole, inferring missing parts. The ability to infer what a speaker meant, even if he/she did not actually say it.

It is these factors that make NLs so difficult to process by computer -- but therefore so fascinating to study. 6 Syntactic ambiguity I saw her duck The man closed the door with a bang The man closed the door with the black and white stripes 7

Semantic ambiguity The man went over to the bank Mary loved Bill. Mary loved potato chips. Water runs down the hill. The road runs down the hill 8 Phonological ambiguity Within words Input, intake, income Imput, intake, iNcome (N=ng)

Across word boundaries When playing football, watch the referee When talking about other people, watch whos listening When catching a hard ball, wear gloves Homophones Im a writer and I write books Im a rider and I write books 9

10 Discourse Anaphora London had snow yesterday It also had fog It fell to a depth of one meter It will continue cold today Speaker intentions Can you swim Can you tell me the time?

Can you pass the salt? Inference You shouldnt lend John any books. He never returns them. 11 Language technology ALICE the chatbox Jabberwacky

USC demo for learning Arabic mov 12

Recently Viewed Presentations

  • Introduction to Computing and Programming in Python: A ...

    Introduction to Computing and Programming in Python: A ...

    * Key point: What we're talking about here is not just for JES, or even just for Jython. You can do this in any Python implementation anywhere. * Numeric is a general number. By specifying the kind of the number,...
  • Chapter 4: More on Two-Variable Data

    Chapter 4: More on Two-Variable Data

    Chapter 4: More on Two-Variable Data. Categorical Variables. Use counts or percentages that fall into various categories. Organized into two-way tables. Two-way tables describe two categorical variables. Rows make up one variable; columns make up the other.
  • Chemical BONDING IONIC Lewis Dot Diagrams Sodium Chloride

    Chemical BONDING IONIC Lewis Dot Diagrams Sodium Chloride

    Chemical BONDING IONIC Lewis Dot Diagrams Sodium Chloride This is the finished Lewis Dot Structure [Na]+1 [ Cl ]-1 How did we get here? Practice Dot diagrams & formulas Lithium fluoride Magnesium oxide Calcium chloride Potassium hydride Drawing molecules using...
  • A Machine Learning Approach to Linking FOAF Instances

    A Machine Learning Approach to Linking FOAF Instances

    Michael Phelps swimmer 1985- Michael Phelps biophysicist 1939- Michael Phelps is the scientist most often identified as the inventor of PET, a technique that permits the imaging of biological processes in the organ systems of living individuals. Phelps has ...
  • How Can I Be Sure?

    How Can I Be Sure?

    Mae posib camliwio'r gwir e.e. "Dydy'r hyn sy'n wir i ti ddim yn wir i mi". Ffeithiau Pwysigrwydd addewidion ac awdurdod yr ysgrythur. Hanes Job, a'i sicrwydd fod Duw yn dal yno pan oedd ei ysbryd yn isel. Canlyniad negyddol...

    Cruz (2007) states that some educators incorporate video games into their lessons both to catch and keep the attention of the students and to enhance course content. Many business, medicine, and law schools are using video games like Kristen's Cookies,...
  • The Language of Poetry

    The Language of Poetry

    Beowulf or Hercules. Assonance: the repetition of vowel sounds in non-rhyming words. Example: Up above the world so high/ Like a diamond in the sky. ... A lyrical poem of sorrow or mourning for the dead; also, a reflective poem...
  • Citation VII Flash Cards Copyright  2013 CAE 1

    Citation VII Flash Cards Copyright 2013 CAE 1

    Illumination indicates the electric auxiliary hydraulic pump is activated. The pump comes ON if one of the following occurs: AUX hydraulic pump switch selected ON. AUX hydraulic pump switch in NORM and system pressure less than 1,200 PSI. AUX hydraulic...