Some extra stuff

1
Some extra stuff

• Semantic change that results in an antonym of the
  original word
• awful original meaning 'awe-inspiring, filling
  (someone) with deep awe', as in the awful majesty
  of the Creator new meaning 'breath-takingly
  bad so bad that it fills (a person) with awe and
  amazement'
• Compare it to awesome
• Similar pair terrible vs. terrific

2
Some extra stuff

• cool vs. hot they could be both positive (e.g.
  Thats really cool hot buys) but not always
  (e.g. hot check)
• Intermediate ones like lukewarm do not have
  positive or negative meanings.

3
Computational Linguistics

• Ling 400

4
What is Linguistics good for?

• Language teaching
• Medical speech therapy for aphasic patients
• Computer-related applications
• Computational linguistics (also called natural
  language processing, language engineering)
  computer simulation of human language processes

5
Some online materials

• Some relevant information including a lecture by
  Prof. Emily Bender is available from the
  following web site.
• http//depts.washington.edu/llc/olr/linguistics/in
  dex.php

6
Computational Linguistics

• encoding/production speech synthesis, word
  processing help, production side of an expert
  system, generation of sentences in the target
  language in machine translation.
• decoding/understanding speech recognition,
  parsing, disambiguation via a network of semantic
  relations.

7
Language Production

• thinking cannot be simulated
• speech/writing computer simulation of speech
  sounds is possible to some extent. Computer can
  help this process with a grammar checker, an
  input system and a word breaker (in a language
  like Japanese). But these tasks do not simulate
  what people actually do when they talk.

8
Language Production (2)

• Though not part of the natural production
  process, turning speech into written text has
  some practical applications.
• This is very useful because speaking is usually
  quicker than writing. It would be like having a
  personal secretary.
• This is also useful for someone who cannot write
  because of disability or injury.

9
Language Understanding

• speech recognition difficult but possible if the
  domain is restricted (e.g. speaker and/or
  expected input types) Why is this difficult?
• syntactic analysis parsing (syntactic analysis
  by computer) is possible but needs
  semantic/pragmatic information for disambiguating
  instances of structural ambiguity.
• Interpretation (truth conditions) unclear as to
  how to simulate this usually done via semantic
  representations (in some machine translation
  systems).

10
Ambiguity Resolution

• The astronomer saw a comet with a telescope.
• The astronomer saw a comet with a brilliant tail.
• How do we solve its ambiguity?
• One needs to know some information about seeing
  and comets.

11
Semantic Network
12
Concrete Applications

• corpus linguistics
• machine translation
• text retrieval
• text summarization
• word processing help (discussed above)
• expert systems
• speech recognition/synthesis (touched upon above)
• toys, games
• automatic telephone interpretation system
• ultimately artificial intelligence, robotics

13
Corpus Linguistics

• This is a generic name for various computer
  applications that make use of large language
  databases (called corpora)
• Having access to a large database enabled us to
  process linguistic data in a statistical way,
  rather than in an analytical way.
• This conflict of two opposing views (statistical
  vs. analytical) is very apparent in machine
  translation.

14
Machine Translation (1)

• text-to-text translation (great need for
  translation at UN, EC (European Community)
• Works best when two languages in question are
  similar in structure
• Usually, pre-editing and/or post-editing by a
  human translator is required machine-assisted
  translation.

15
Machine Translation (2)

• Traditionally, MT required parsing, possibly some
  semantic analysis, then mapping to a syntactic
  tree of the sentence in the target language.
• An alternative is appeal to statistical means of
  mapping a surface string in the source language
  to a surface string in the target language.
• http//www.excite.co.jp/world/english/web/

16
Machine Translation (3)

• Difficulty with word-for-word translation
• Watasi-ni-wa futari kodomo-ga imasu.
• I -at-top two child-nom exist
• Literally, As for me as a location, two
  children exist
• Actually, its meaning is I have two children.

17
Computational Semantics

• The study of how to automate the process of
  constructing and reasoning with meaning
  representations of natural language expressions.
• This could play an important role in such
  application areas as machine translation when two
  typologically distinct languages are involved
  (e.g. English and Japanese).

18
Text Retrieval

• key word ? text/book
• key word morphology
• Principles of Polymer Morphology
• Image Analysis and Mathematical Morphology
• Drainage Basin Morphology
• French Morphology
• We need morphological, syntactic, and semantic
  information to find the right text/book.
• Further applications search engines, etc.

19
Text Summarization

• We need to be able to select the right
  information from the electronic documents
  available (esp. on the web).
• Automatic text summarization is a technique that
  can help people to quickly grasp the concepts
  presented in a document by creating an abstract
  or summary of the original text.

20
Semantic Web

• Some people (e.g. Evergreen U) are trying to
  classify contents of web pages so that they are
  meaningful to computers. But this is not an easy
  task since the categories must presumably be
  pre-selected by people.
• The semantic Web provides a common framework that
  allows data to be shared and reused across
  application, enterprise, and community
  boundaries. http//www.w3.org/2001/sw/

21
Speech Recognition/Synthesis

• actually being used on personal computers (on a
  limited basis), automated telephone answering
  system, etc.
• Application of acoustic phonetics, phonology

22
AI and robotics
Furby
Aibo