Natural Language Processing in Alternative and Augmentative Communication
Published on: Mar 3, 2016
Transcripts - Natural Language Processing in Alternative and Augmentative Communication
PROCESSING IN ALTERNATIVE
3RD YEAR B.TECH – IT
NATURAL LANGUAGE PROCESSING
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.
-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
Explicit depiction of facts about language through well-understood
knowledge schemes and algorithms
Deep analysis of linguistic phenomena
Uses mathematical techniques and large texts of corpora without
incorporating world knowledge
Output produced by each state has a definitive probability
Combines statistical learning with various representation theories
Allows transformation, inference and logic formulae manipulation
Less constrained architecture
• In terms of gold-standard
• In terms of overall tasks
• Quality of process, result
• Design, Algorithm, Resources
• Objective Evaluation
• Subjective Evaluation
DATA FLOW DIAGRAM - NLP
AUGMENTATIVE AND ALTERNATIVE
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
Two groups of communication
Unaided – Gestures, hand signs,
Aided – Communication boards /
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
Improving Pragmatics, Contextual resources
Lexicon and Methodology
Efficient keyboard setup, Proper word prediction, Structure
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
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
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
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.
Full phrase or
I am typing my di………
ABC DEF GHI
STU VW XYZ
error space . , / ?
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 :
Natural Language Processing can be effectively integrated
into Augmentative and Alternative Communication.
Techniques are developed to overcome the issue of Data
AAC systems are more flexible, expressive tools with
enhanced rate of computation when incorporated with NLP
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.
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