NATURAL LANGUAGE
PROCESSING IN ALTERNATIVE
AND AUGMENTATIVE
COMMUNICATION
S.R.JHANANI
S.DIVYA
3RD YEAR B.TECH – IT
MEENAKS...
NATURAL LANGUAGE PROCESSING
 HUMAN-COMPUTER INTERACTION
 Goal - “to achieve human-like language processing”.
 Encompass...
LEVELS
PHONOLOGY
MORPHOLOGY
LEXICAL
SYNTACTIC
SEMANTIC
DISCOURSE
PRAGMATIC
-Interprets sounds within and across words
-Bre...
APPROACHES
1. Symbolic
 Explicit depiction of facts about language through well-understood
knowledge schemes and algorith...
STAGES
PARSING TRANSLATING
GENERATING
INPUT
1. Phonology
2. Morphology
3. Lexical
4. Syntactic
5. Semantic
6. Discourse
7....
EVALUATION TYPES
• In terms of gold-standard
• In terms of overall tasks
Intrinsic vs.
Extrinsic
• Quality of process, res...
DATA FLOW DIAGRAM - NLP
AUGMENTATIVE AND ALTERNATIVE
COMMUNICATION
 Way to communicate when one does
not have the physical ability to use
verbal ...
ROLE OF NLP IN AAC
 Common concept – INFORMATION RETRIEVAL
 Obtains information relevant to the input
 Factors : Syntac...
Cont’d…
The sentence “Work I Done” is presented as follows
 Step 1: The words in the sentence are broken separately. The
...
COMPANSION
 Includes abbreviation expansion, character prediction, word
and string prediction, reduced disambiguation and...
ASSESSMENT
 AAC system tends not only to serve as an aid for communication
but also to improve the language intelligibili...
CONCLUSION
 Natural Language Processing can be effectively integrated
into Augmentative and Alternative Communication.
 ...
REFERENCES
 Jurafsky, James (2008). Speech and Language Processing. An
Introduction to Natural Language Processing, Compu...
Natural Language Processing in Alternative and Augmentative Communication
of 15

Natural Language Processing in Alternative and Augmentative Communication

Published on: Mar 3, 2016
Source: www.slideshare.net


Transcripts - Natural Language Processing in Alternative and Augmentative Communication

  • 1. NATURAL LANGUAGE PROCESSING IN ALTERNATIVE AND AUGMENTATIVE COMMUNICATION S.R.JHANANI S.DIVYA 3RD YEAR B.TECH – IT MEENAKSHI SUNDARARAJAN ENGINEERING COLLEGE
  • 2. NATURAL LANGUAGE PROCESSING  HUMAN-COMPUTER INTERACTION  Goal - “to achieve human-like language processing”.  Encompasses the automation of linguistic forms, activities or methods of communication.  Presently implemented using machine learning algorithms. Previously – Decision trees Now – Statistical methods  Future – Unsupervised, Semi-supervised algorithms. HUMAN COMPUTER PROCESSING COMMUNICATE AI Ling uistic s NLP
  • 3. LEVELS PHONOLOGY MORPHOLOGY LEXICAL SYNTACTIC SEMANTIC DISCOURSE PRAGMATIC -Interprets sounds within and across words -Breaks down words into morphemes -Assign meanings to individual words -Check if sentence is grammatically correct -Performs disambiguation of words -Makes connection between sentences -Uses contextual and situational meanings
  • 4. APPROACHES 1. Symbolic  Explicit depiction of facts about language through well-understood knowledge schemes and algorithms  Deep analysis of linguistic phenomena 2. Statistical  Uses mathematical techniques and large texts of corpora without incorporating world knowledge  Output produced by each state has a definitive probability 3. Connectionist  Combines statistical learning with various representation theories  Allows transformation, inference and logic formulae manipulation  Less constrained architecture
  • 5. STAGES PARSING TRANSLATING GENERATING INPUT 1. Phonology 2. Morphology 3. Lexical 4. Syntactic 5. Semantic 6. Discourse 7. Pragmatic
  • 6. EVALUATION TYPES • In terms of gold-standard • In terms of overall tasks Intrinsic vs. Extrinsic • Quality of process, result • Design, Algorithm, Resources Black-box vs. White- box • Objective Evaluation • Subjective Evaluation Automatic vs. Manual
  • 7. DATA FLOW DIAGRAM - NLP
  • 8. AUGMENTATIVE AND ALTERNATIVE COMMUNICATION  Way to communicate when one does not have the physical ability to use verbal speech or writing.  AAC systems - Designed to help people express their thoughts, needs, wants and ideas.  Access methods used - direct selection by pointing / reaching /canning using a switch connected to the device / eye gaze  Two groups of communication  Unaided – Gestures, hand signs, expressions  Aided – Communication boards / devices
  • 9. ROLE OF NLP IN AAC  Common concept – INFORMATION RETRIEVAL  Obtains information relevant to the input  Factors : Syntactic, Ambiguity  ME / SEE / CAT / TO EAT = I saw the cat eating.  CAT / TO EAT / SEE / ME =The cat ate and I saw it (or) The cat that ate saw me.  Goal – Enhance communication rate without limiting their expressing capability.  Solutions –  Improving Pragmatics, Contextual resources  Lexicon and Methodology  Efficient keyboard setup, Proper word prediction, Structure prediction.
  • 10. Cont’d… The sentence “Work I Done” is presented as follows  Step 1: The words in the sentence are broken separately. The result is: “Work, I, Done”.  Step 2: The semantic parser parses the words and matches the words with the appropriate grammar. Subsequently, the context is also analyzed.  Step 3: The words are also compared with relevant aids such as pictures to identify the relations and patterns of them.  Step 4: The semantic strategy gives the result as “Work Is Done by Me”.  Step 5: The results of the strategy are considered and the individual’s cognitive level is evaluated.  Step 6: If the cognitive level is very low, the picture-based communication is made. If it is medium, then paper based or even speech-based communication can be made to convey the end result.
  • 11. COMPANSION  Includes abbreviation expansion, character prediction, word and string prediction, reduced disambiguation and special keywords, symbolic entry and coding methods.  Text-Entry inteface driven by continuous pointing gestures  Eye-trackers, Joysticks and Touch-screen  Mouse; Novices- 25 words per minute, experienced users - 39 words per minute. Uninflected content words Full phrase or Sentence I am typing my di……… 1. dish 2. divide 3. distance 4. dissertion 5. dimple ABC DEF GHI MNO PQR STU VW XYZ JKL error space . , / ?
  • 12. ASSESSMENT  AAC system tends not only to serve as an aid for communication but also to improve the language intelligibility. Issues in AAC :  No pre-stored samples to the patients in the AAC systems  No option for dynamic choice of the vocabulary in an AAC system. Application of NLP to AAC :  The language representation of NLP is easier  Enables better interpretation and automatic content maintenance Two majorly useful fields :  Interface design  Word prediction
  • 13. CONCLUSION  Natural Language Processing can be effectively integrated into Augmentative and Alternative Communication.  Techniques are developed to overcome the issue of Data Collection  AAC systems are more flexible, expressive tools with enhanced rate of computation when incorporated with NLP methodologies.  AAC system assures clarity of information through different means for users.  The application of NLP in AAC is expected to develop a new world of communication in terms of clarity and ease in understanding and capabilities.
  • 14. REFERENCES  Jurafsky, James (2008). Speech and Language Processing. An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition (in English) (2nd ed.). Upper Saddle River (N.J.): Prentice Hall.  Roger Schank, 1969, A conceptual dependency parser for natural language Proceedings of the 1969 conference on Computational linguistics, Sång-Säby, Sweden pages 1-3  McCorduck 2004, p. 286, Crevier 1993, pp. 76−79, Russell & Norvig 2003, p. 19  http://en.wikipedia.org/wiki/Natural_language_processing  http://en.wikipedia.org/wiki/Augmentative_and_alternative_commu nication  http://www.asha.org/NJC/faqs-aac-basics.htm

Related Documents