LELA300431 Language and Computers

1
LELA300431Language and Computers

• Harold Somers
• Professor of Language Engineering

2
Computers and Language?

• Getting computer to handle language in a natural
  way
• As part of interface with user (eg alternatives
  to keyboard/mouse input, text output, support for
  the disabled)
• consulting databases to get information (e.g.
  library catalogue, train timetable, banking)
• As a task in itself specifically linguistic
  purposes (e.g. dictation, translation,
  summarizing, report writing, language teaching)
• Using computer to do linguistics
• Synonyms (or components?)
• Natural Language Processing
• Computational Linguistics
• Language Engineering
• Basic tools, techniques and models
• Applications

3
Syllabus

• Survey of applications
• Elements of language, levels of linguistic
  processing
• Sound (speech recognition, synthesis)
• Writing (OCR, handwriting, character sets,
  spelling)
• Words (lexicon, morphology)
• Sentences (syntax)
• Semantics, Pragmatics
• Branches of language/linguistics
• Psycholinguistics and AI
• Applied linguistics (teaching, translation)
• Information retrieval
• Or your choice of anything else relevant
  (historical, socio, etc.)

4
Mon 10am Newman/G16 Fri 10am AlanTuring/G205
1. Introduction Sept 24, 28 Introduction, explanation of syllabus What makes language hard for computers? Applications overview
2. Phonetics Oct 1, 5 Speech recognition Speech synthesis
3. Writing Oct 8, 12 Character sets, Unicode, input methods Spell checkers, grammar checkers
4. Words Oct 15, 19 Dictionaries, Thesauri WordNet
5. Morphology Oct 22, 26 Morphology Tagging
READING WEEK
6. Syntax Nov 5, 9 Parsing I Parsing II
7. Semantics,Pragmatics Nov 12, 16 Dialogue understanding Text generation, Cooperative responses
8. Branches Nov 19, 23 Psycholinguistics language and AI Applied linguistics CALL
9. Applied linguistics Nov 26, 30 CALL Translation aids
10. Translation Dec 3, 7 Machine translation I Machine Translation II
11. Information retrieval Dec 10, 14 Text retrieval Summarization Question answering, text mining
These lectures to be rearranged due to HSs
absence
5
Assessment

• Examination 50 multiple choice (or short
  phrase) answers
• Essay 3000 word essay due in at the start of
  the exam period
• Choose a particular NLP application, and explain
  the difficulties that natural language poses to
  the computer, and how (or whether) they are
  addressed.
• How is the study of language relevant to NLP?
  Focus on one or two areas of NLP only.
• Choose one branch of language study (eg
  historical, sociolinguistics, psycholinguistics,
  child language, applied linguistics, etc.) and
  discuss what role the computer, and in particular
  computational linguistics, could play.
• (Note that all involve taking lectures as
  starting point, and going into more detail, based
  on your own research)

6
What is NLP?
Language and Linguistics
7
Language and AI

• language ability is an integral part of
  Artificial Intelligence, which relates to
  robotics
• Computers in SciFi use language readily how
  realistic is this? What are the problems?
• HAL in 2001 A Space Odyssey (1968)

8
How realistic is HAL?

• Non-linguistic functions include...
• monitoring and controlling the spaceship
• playing chess
• vision
• general reasoning about the world
• especially this particular mission

9
HALs use of language

• He has to use language to communicate with the
  crew, including ...
• chatting sociably
• discussing general and specific conditions in the
  spaceship
• understanding commands
• initiating conversations, whether work or play

10
What is language?

• spoken vs. written language
• speaker vs. hearer production vs. analysis
• different levels of language
• different functions of language

11
Computer speech

• for natural-sounding speech, computer must get
  individual sounds right, but also combine them
  correctly
• intonation
• stress (pitch, loudness, length)
• pace (pauses can be significant)

12
Speech understanding

• signal processing (acoustic physics)
• separating speech from background noise
• recognizing individual speech sounds (humans can
  make very fine distinctions)
• Its hard to wreck a nice beach
• What dimes a necks drain to stop port?
• variability in human voices

13
Problems with language in general

• Words are ambiguous (bank, round, take)
• Sentences are ambiguous
• The chicken is ready to eat
• Visiting relatives can be boring
• End to free school looms
• The man saw the girl with a telescope
• Remove bulb, cover, and replace

14
Pragmatic problems

• We dont always say what we mean
• Can you pass the salt?
• Its cold in here, isnt it?
• Im sorry ( Say it again)
• Do you want some more? Youre alright.
• We dont always mean what we say
• Its raining cats and dogs
• I could murder a sandwich

15
Solutions

• Linguistics (grammar)
• can often tell us which interpretations are
  possible, including limited aspects of meaning,
  e.g. The man saw the girl with a hat
• Restricted domain if we know what the subject
  is, a lot of ambiguity disappears
• Context
• Real-world knowledge

16
Next up

• A whistle-stop tour of applications and what they
  involve
• Then down to business!