1 / 17

CS4705 Natural Language Processing Fall 2010

CS4705 Natural Language Processing Fall 2010. What is Natural Language Processing?. Designing software to recognize, analyze and generate text and speech Current real world applications

nancy
Download Presentation

CS4705 Natural Language Processing Fall 2010

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. CS4705 Natural Language Processing Fall 2010 CS 4705

  2. What is Natural Language Processing? • Designing software to recognize, analyze and generate text and speech • Current real world applications • Searching very large text and speech corpora: e.g. the Web, Facebook, online news sources, telephone calls • Translating from one language to another: e.g. Arabic/English, • Summarizing very large amounts of text or speech: e.g. your email, the news • Building spoken dialogue systems: e.g. Amtrak’s ‘Julie’

  3. What’s the Problem? • Something Went Wrong In Jet Crash, Expert Says • Police Begin Campaign To Run Down Jaywalkers • Drunk Gets Nine Months In Violin Case • Farmer Bill Dies In House • Iraqi Head Seeks Arms • Enraged Cow Injures Farmer With Ax • Stud Tires Out • Eye Drops Off Shelf • Teacher Strikes Idle Kids • Squad Helps Dog Bite Victim

  4. What will we learn about in this course? • Morphology: the way words are formed • Syntax: the way words are grouped together into larger constituents and phrases and the way these phrases can be ordered – how sentences are related • Semantics: the context-independent ‘meaning’ of utterances • Pragmatics: the context-dependent ‘meaning’ of utterances • Goal: what is a speaker/writer meaning to convey

  5. Morphology Stud tires out: Is `Tires’: a noun or a verb? • Internet search: `union activities in New York’ • What to look for? • Union/unions; activities/activity • Active? Action? Actor? • New vs. New York

  6. Syntax • Constituent Structure: • Teacher Strikes Idle Kids • Enraged Cow Injures Farmer With Ax • Word Order and Meaning • John hit Bill. • Bill was hit by John. • Bill, John hit. • Who John hit was Bill. • I said John hit Bill. • John hits Bill.

  7. Semantics • Word meaning • John picked up a bad cold. • John picked up a large rock. • John picked up Radio Netherlands on his radio. • Is meaning compositional? • Squad helps dog bite victim • Enraged cow injures farmer with ax

  8. Pragmatics • “Going Home'' -A play in one act (thanks to Bonnie Dorr) • Scene 1: Pennsylvania Station, NY • Bonnie: Long Beach? • Passerby: Downstairs, LIRR Station. • Scene 2: Ticket Counter, LIRR Station • Bonnie: Long Beach? • Clerk: $4.50.

  9. Scene 3: Information Booth, LIRR Station • Bonnie: Long Beach? • Clerk: 4:19, Track 17. • Scene 4: On the train, vicinity of Forest Hills • Bonnie: Long Beach? • Conductor: Change at Jamaica. • Scene 5: On the next train, vicinity of Lynbrook • Bonnie: Long Beach? • Conductor: Right after Island Park.

  10. Algorithms • Rule-based • Symbolic Parsers and morphological analyzers • Finite state automata • Probabilistic/statistical • Learned from observation of (labeled) data • Predicting new data based on old • Machine learning

  11. Current Real-World Applications • Search: very large corpora, e.g. Google • Question answering: e.g. IBM’s Jeopardy!, DARPA who/what/where…, Ask Jeeves • Translating between one language and another: e.g. Google Translate, Babelfish • Summarizing very large amounts of text or speech: e.g. your email, the news, voicemail • Sentiment analysis: restaurant or movie reviews • Dialogue systems: e.g. Amtrak’s ‘Julie’

  12. Instructor • Julia Hirschberg • CEPSR 705, julia@cs.columbia.edu • Focus: Spoken Language Processing • Lab: The Speech Lab, CEPSR 7LW3-A • Research: • Deceptive speech • Charismatic speech: • Emotional speech: anger, uncertainty • Speech summarization: Broadcast News • Spoken Dialogue Systems: Games Corpus • `Translating Prosody’: English – Mandarin • Text2Scene Synthesis

  13. Course Details • Teaching Assistant: Mohamed Altantawy • (ma2795@columbia.edu) • Office Hours: CEPSR 7LW1 (Speech Lab), W 5-6, Th 5:30-6:30 • Syllabus http://www1.cs.columbia.edu/~julia/courses/CS4705/syllabus10.htm

  14. Text: Daniel Jurafsky and James H. Martin, Speech and Language Processing, second edition • Note errata available on website • Check courseworks for additional information on class, homework assignments, posting questions • Assignments: • 3 homework assignments: Question-answering, text classification, parsing • Midterm and final exams • Five ‘free’ late days for homeworks – not usable on HW1 though – after that 10% off per late day • You will need a CS account

  15. Grading • HW1: 10% • Hw2: 20% • Hw3: 20% • Midterm: 15% • Final: 25% • Class participation: 10%

  16. Academic Integrity Copying or paraphrasing someone's work (code included), or permitting your own work to be copied or paraphrased, even if only in part, is forbidden, and will result in an automatic grade of 0 for the entire assignment or exam in which the copying or paraphrasing was done. Your grade should reflect your own work. If you are going to have trouble completing an assignment, talk to the instructor or TA in advance of the due date please. Everyone: Read/write protect your homework files at all times.

  17. For Next Class • Look at syllabus – ask questions about anything you don’t understand • Read Chapters 1-2 of J&M

More Related