1 / 12

“ Open the pod bay doors, HAL.” “I’m sorry Dave, I’m afraid I can’t do that.”

Natural Language Processing (or “NLP”) Reading: Chapter 1 from Jurafsky and Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition (linked to class website). “ Open the pod bay doors, HAL.”

erwin
Télécharger la présentation

“ Open the pod bay doors, HAL.” “I’m sorry Dave, I’m afraid I can’t do that.”

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(or “NLP”)Reading:Chapter 1 from Jurafsky and Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition(linked to class website)

  2. “Open the pod bay doors, HAL.” “I’m sorry Dave, I’m afraid I can’t do that.”

  3. What is involved in NLP? Phonetics / Phonology: Recover sequence of words from audio signal. “Open the pod bay doors, HAL.”

  4. What is involved in NLP? Phonetics / Phonology: Recover sequence of words from audio signal. “Open the pod bay doors, HAL.”

  5. Text-To-Speech: Take a sequence of words and generate an audio signal. “I’m sorry Dave, I’m afraid I can’t do that.”

  6. Morphology: Recognize plurals, contractions, etc. “Open the pod bay doors, HAL.” “I’m sorry Dave, I’m afraid I can’t do that.”

  7. 1: Open the pod bay doors, HAL.Parses found: 1     [1]   <SENTENCE> <CENTER>-| <IMPERATIVE> | <VO> | <LVR>-| | Open ................... <*V> | | v: open <OBJECT>-| | <NSTGO> | <NSTG> | <LNR> | <LN>-| | <TPOS>-| | | <LTR> | | | the ....... <*T> | | | <NPOS>-| | | <NNN> | | pod ....... <*N>-| | | n: pod bay ....... <*N>-| | | n: bay <NVAR>-| | doors ........... <*N> | | n: door <COMMASTG>-| | , .............. , | | <RN>-| | <APPOS> | <LNR> | <NVAR> | HAL ..... <*N> | <ENDMARK>-| Syntax: Parse utterance Determine type of utterance (e.g., question, request, command)

  8. Lexical Semantics: Determine meaning of component words • 1: Open the pod bay doors, HAL.Parse Nr: 1 • Open • v: open • 1. open, open_up -- (cause to open or to become open; "Mary opened the car door") • pod • n: pod • 4. fuel_pod, pod -- (a detachable container of fuel on an airplane) • bay • n: bay • 1. bay -- (an indentation of a shoreline larger than a cove but smaller than a gulf) • doors • n: door • 1. door -- (a swinging or sliding barrier that will close the entrance to a room or building; "he knocked on the door"; "he slammed the door as he left")

  9. Compositional semantics: Determine meaning from combination of these components. window door open action ingress egress kind of kind of kind of applies to applies to kind of kind of

  10. Pragmatics: Adapt phrasings to current situation, to accomplish goals. E.g., politeness: “I’m sorry Dave, I’m afraid I can’t do that.”

  11. Discourse: Conversational behavior follows conventions (don’t interrupt, respond to requests and questions, etc.)

  12. NLP does all this, plus dealing with ambiguity in language • “I made her duck” • Meanings?

More Related