1 / 23

Natural Language Processing

Natural Language Processing. Daniele Quercia Fall, 2000. Presentation Outline. Introduction to the Natural Language Processing (NLP) Applications of NLP Discussion. Introduction to Natural Language Processing (NLP). Representation of the input meaning. Natural Language (English).

havard
Download Presentation

Natural Language Processing

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. Natural Language Processing Daniele Quercia Fall, 2000

  2. Presentation Outline • Introduction to the Natural Language Processing (NLP) • Applications of NLP • Discussion

  3. Introduction to Natural Language Processing (NLP)

  4. Representation of the input meaning Natural Language (English) NLP • What is Natural Language processing (NLP)? • “The Natural Language Processing (NLP) is the engineering of systems that process or analyse written or spoken natural language.” • NLP • System • (computational model)

  5. Psychology • Neuroscience • Natural • Language • Processing • Computer Science • Linguistics Related disciplines

  6. A possible file: • PIPPO.TXT • Hallo Pippo. • Ciao Pippo. • Auf widersehen Pippo. • Unix wc program • total number of • bytes, • words, • lines • in a text file. • What is a word? Knowledge of language • These language processing applications use knowledge of language

  7. Knowledge of language - 2 • Types of knowledge used in NLP • Phonetics and Phonology • Morphology • Syntax • Semantics • Pragmatics • Discourse • NLP can be viewed as resolving ambiguity at one of these levels.i

  8. Knowledge of language - 3 • Example: HAL computer system. • capable of interacting with humans • Stanley Kubrik’s film • 2001: A Space Odissey • Conversation between HAL and Dave

  9. Knowledge of language - 4 • Example(cont’d): HAL computer system. • capable of interacting with humans • Stanley Kubrik’s film • 2001: A Space Odissey • Dave: Open the pod bay doors, right now. • HAL: I’m sorry Dave, I’m afraid I can’t do that.

  10. Syntax • The study of the structural relationship between words • but syntax don’t tell us much about the meaning … • e.g. : • I saw the Grand Canyon flying to New York • Time flies like an arrow Knowledge of language - 5 • Phonetics and Phonology • The study of linguistic sounds • How word are pronounced in colloquial speech

  11. Semantics • The study of meaning • e.g. : • I work for J.F. Zich • and he’s a good boss • which is a good company • Pragmatics • The study of how language is used to accomplish goals • e.g. • Can youn tell me what time is it? • Could I have the salt? Knowledge of language - 6

  12. Morphology • The study of the meaningful components of words. • e.g. : • Kick, kicks, kicked, kicking • Arm, army Knowledge of language - 7 • Discourse • The study of linguistic linguistic units larger than a single utterance

  13. Applications of NLP

  14. Machine translation • Information retrieval Applications of NLP • Text-based applications • Dialogue based applications • Speech recognition

  15. Applications of NLP • Machine translation • Automatic machine translation • translates texts from one language to another • Important constraint • The text needs to be restricted to a limited range of subjects • Windows 98 deve essere distribuito • senza Internet Explorer o insieme al navigatore del concorrente Netscape • Windows 98 must be delivered either without Internet Explorer or in connection with the sailor of the competitor Netscape

  16. Applications of NLP • Machine translation • even the best system produces poor translation… • … but Machine-assisted translation uses a computer to help a translator.

  17. Applications of NLP • Information retrievial • concerns the retrieving of relevant information from databases.

  18. Applications of NLP • Information retrievial (cont’d) • Inverted index • Retrieval depends only on how often each word appears in a document • Should we treat all words equally?

  19. Applications of NLP • Information retrievial (cont’d) • Stop list: words to ignore • Many frequent words in English are function words, which are useless.

  20. Applications of NLP • Speech recognition • Speech generation is comparatively easy, but recognition is hard ! • The acoustic signal is highly ambigous • Disambiguation using statistics • If …they buy… occurs more frequently than …they by …, it will chosen

  21. Conclusions

  22. Conclusions • Computers can process natural language in a variety of interesting ways • A computer can’t do anything close to “understanding” language … • NLP is almost never error-free

  23. A very special thanks to …

More Related