Language Processing: Humans & Computer

1
Language Processing Humans Computer
Psycholinguistics Computational Linguistics

• Lauren Kafka
• Marina Hamoy
• August 3, 2006

2
Psycholinguistics

• The area of linguistics that is concerned with
  linguistic performancehow we use our linguistic
  competencein speech (or sign) production and
  comprehension.

3
The Speech Chain Brain-to-Brain Linking

• A spoken utterace starts as a message in the
  speakers brain/mind.
• The message is put into linguistic form and
  interpreted as articulation commands.
• It emerges as an acoustic signal.
• The signal is processed by the listeners ear and
  sent to the brain/mind, where it is interpreted.

4
Comprehension

• One goal of psycholinguistics is to describe the
  processes people normally use in speaking and
  understanding language.
• Breakdowns in performance such as
  tip-of-the-tongue phenomena, speech errors, and
  failure to comprehend tricky sentences tell us a
  lot about how language is processed.

5
Can you think of any of your own?

• Examples of when some word was on the
  tip-of-your-tongue, but you couldnt think of it
• Speech errors (Hung go)
• Failure to comprehend tricky sentences
• http//www.zippyvideos.com/5589295543497276/time_o
  ut-1/original

6
Speech Sounds Understanding Begins with Hearing

• Sound is produced whenever there is a disturbance
  in the position of air molecules.
• Acoustic phonetics is concerned only with speech
  sounds, all of which can be heard by the normal
  human ear.

7
Frequency, Pitch Volume

• The speed of the variations of air pressure
  determines the fundamental frequency of sounds.
• This is perceived by the hearer as pitch.
• The magnitude, or intensity, of the variations
  determines the loudness of the sound.

8
Speech Perception

• The speech signal can be broken into strings of
• Phonemes
• Syllables
• Morphemes
• Words
• Phrases

9
Context Lexical Access

• Night rate vs. nitrate depends on context
• Meaning of words depends on lexical access or
  word recognition
• Example A sniggle blick is procking a slar.
• If you dont recognize the words, you conclude
  that the sentence is nonsense.

10
Lexical Semantics

• Processing speech to get at the meaning of what
  is said requires syntactic analysis as well as
  knowledge of lexical semantics.
• Stress and intonation provide some clues to
  syntactic structure. Example He lives in the
  white house. He lives in the White House.
• Loudness, pitch, and duration of syllables
  provide information about meaning.

11
Timing Rhythm

• I vant to sock your blut.
• Ivan tsuckyour blut.
• Ted Koppel gave an address.
• Ted Koppel gave Ann a dress.
• Can you think of two sentences that include the
  same letters or sounds, but differ in timing,
  rhythm, and meaning?

12
Language Analysis
Computer Technology

• Machine translation (MT)
• Between natural languages
• Analysis of authentic materials
• Communication between people computers
• Artificial intelligence (AI)
• World Wide Web (www)
• Research in linguistic theories

13
Frequency Analysis

• Corpus 1M spoken or written language data
  gathered for linguistic research or analysis
• Frequency analysis
• SAE 30 - and, the, to, that, of, a, I, you, it,
  know
• WAE 25 - the (7), of, and, to, a, that, in,
  is, was, he
• English prepositions WAE (except TO)
• Profane/taboo SAE
• http//textalyser.net/

14
Concordance Analysis

• http//www.dundee.ac.uk/english/wics/wics.htm

15
CollocationAnalysis

• 2 or more words with customary relationships
• http//esl.about.com/library/vocabulary/blcollocat
  ion_1.htm

16
Information Retrieval WWW

• Search engines
• Databases
• http//www.language-archives.org/index.html
• Prevent spammers from scanning your e-mail
  address by clicking on the active e-mail link
  by using a simple JavaScript code

17
Data Mining

• Information extraction using keyword queries
• Typical applications customer profiling, fraud
  detection, credit risk analysis, promotion
  evaluation
• Norway to Wal-Mart We don't want your shares -
  Pension-fund investing with a social
  consciousness.
• Intelligence obtained by applying data mining to
  a database of French theses on the subject of
  Brazil

18
Machine Translation

• There's a message coming through, captain -
  TRANSLATION SOFTWARE, the science-fiction dream
  of a machine that understands any language, has
  taken a step closer to reality.
• http//www.gutenberg.org/etext/6737
• free download of literature

19
Computational Phonetics Phonology

• Computers programmed to produce synthetic speech
  by following a recipe of electronic blending
• Speech Recognition
• Speech Synthesis
• TTS difficulties
• gt 300 Heteronyms read reed red
• Inconsistent spelling tough, bough, cough, dough

20
Computational Morphology

• Computers need to understand the inter-weaving of
  rules, exceptions morpheme word structure
• Computers dictionary morphological forms
  needs continual updating
• Form predictability impossible for compounding
  skybox skybox
• Component morpheme
• Monomorpheme or not reZENT or Resent
• Heteronyms - lead leed led

21
Computational Syntax ELIZA

• ELIZA 1st human-machine communication invented
  by J Weizenbaum
• using syntax (print) simulating a psychiatric
  session
• Circuit-Fix-It-Shop NCSU DU repair tech
  programmed speech
• Capable of understanding speaking complex
  utterances
• Computer parser

22
References

• http//www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?
  catalogIdLDC2001T02
• http//www.language-archives.org/index.html
• http//www.gutenberg.org/etext/6737
• http//www.nsknet.or.jp/peterr-s/concordancing/us
  ingconcs.html
• www.otal.umd.edu/SHORE2001/ crossLang/index.html
• http//www.dundee.ac.uk/english/wics/wics.htm
• http//textalyser.net/
• http//www.zippyvideos.com/5589295543497276/time_o
  ut-1/original