| Document Type
|
:
|
BL
|
| Record Number
|
:
|
889932
|
| Main Entry
|
:
|
Mishra, Abhijit
|
| Title & Author
|
:
|
Cognitively inspired natural language processing : : an investigation based on eye-tracking /\ Abhijit Mishra, Pushpak Bhattacharyya.
|
| Publication Statement
|
:
|
Singapore :: Springer,, 2018.
|
| Series Statement
|
:
|
Cognitive intelligence and robotics,
|
| Page. NO
|
:
|
1 online resource (xvii, 174 pages) :: illustrations (some color)
|
| ISBN
|
:
|
9789811315169
|
|
|
:
|
: 9789811315176
|
|
|
:
|
: 9811315167
|
|
|
:
|
: 9811315175
|
|
|
:
|
9789811315152
|
|
|
:
|
9811315159
|
| Bibliographies/Indexes
|
:
|
Includes bibliographical references.
|
| Contents
|
:
|
Intro; Preface; Acknowledgements; Contents; About the Authors; 1 Introduction; 1.1 Cognitive Data: A Valuable By-product of Annotation; 1.2 Human Eye-Movement and Eye-Tracking Technology; 1.2.1 The Visual System: How Do We See?; 1.2.2 Eye-Tracking Technology; 1.2.3 History of Development of Eye-Trackers; 1.2.4 Eye-Tracking Systems: Invasive and Non-invasive; 1.2.5 Tools for Gaze Data Recording and Analysis; 1.2.6 Eye Movement in Reading and Language Processing; 1.3 Theme of the Monograph; 1.3.1 Research Objective 1: Assessing Cognitive Effort in Text Annotation.
|
|
|
:
|
1.3.2 Research Objective 2: Extracting Cognitive Features for Text Classification1.4 Roadmap of the Book; References; 2 Applications of Eye Tracking in Language Processing and Other Areas; 2.1 Eye Movement and Reading: A Psycholinguistic Perspective; 2.1.1 The Eye-Mind Hypothesis: Just and Carpenters' Theory of Reading; 2.1.2 Basic Characteristics of Eye Movement in Reading; 2.1.3 Effects of Lexical and Syntactic Complexities on Eye Movement; 2.1.4 Models for Eye-Movement Control During Reading; 2.1.5 Comparing Eye-Movement Patterns: Measures for Scanpath Similarity.
|
|
|
:
|
2.2 Eye-Movement Behavior and Text Annotation2.2.1 Study of Text Translation Annotation; 2.2.2 Study of Word Sense Annotation; 2.2.3 Study of Sentiment Annotation; 2.2.4 Cognitive Cost Model for Annotation-A Case Study of Named Entity Marking; 2.3 Eye-Movement Data for Development and Evaluation of NLP Systems; 2.3.1 Part-of-Speech Tagging; 2.3.2 Sentence Compression; 2.3.3 Machine Translation Evaluation; 2.4 Eye Tracking: Application Areas Other than Reading and Language Processing; 2.4.1 Neuroscience; 2.4.2 Industrial Engineering and Human Factors.
|
|
|
:
|
2.4.3 Human-Computer Interaction and User Experience2.4.4 Marketing/Advertisement; References; Part I Assessing Cognitive Effort in Annotation; 3 Estimating Annotation Complexities of Text Using Gaze and Textual Information; 3.1 Estimating Text Translation Complexity; 3.1.1 Translation Complexity Index-Motivation, Utility, and Background; 3.1.2 Prediction Framework for Translation Complexity; 3.1.3 Using Eye Tracking for TCI Annotation; 3.1.4 Computing TCI Using Eye-Tracking Database; 3.1.5 Relating TCI to Linguistic Features; 3.1.6 Lexical Features; 3.1.7 Syntactic Features.
|
|
|
:
|
3.1.8 Semantic Features3.1.9 Translation Feature; 3.1.10 Experiment and Results; 3.1.11 Discussion: Correlation Between Translation Complexity and Machine Translation Accuracy; 3.2 Measuring Sentiment Annotation Complexity; 3.2.1 Sentiment Annotation Complexity: Motivation, Utility and Background; 3.2.2 Understanding Sentiment Annotation Complexity; 3.2.3 Creation of Dataset Annotated with SAC; 3.2.4 Eye-Tracking Experimental Setup; 3.2.5 Calculating SAC from Eye-Movement Data; 3.2.6 Linguistic Features for Predicting Sentiment Annotation Complexity; 3.2.7 Predictive Framework for SAC.
|
| Abstract
|
:
|
This book shows ways of augmenting the capabilities of Natural Language Processing (NLP) systems by means of cognitive-mode language processing. The authors employ eye-tracking technology to record and analyze shallow cognitive information in the form of gaze patterns of readers/annotators who perform language processing tasks. The insights gained from such measures are subsequently translated into systems that help us (1) assess the actual cognitive load in text annotation, with resulting increase in human text-annotation efficiency, and (2) extract cognitive features that, when added to traditional features, can improve the accuracy of text classifiers. In sum, the authors' work successfully demonstrates that cognitive information gleaned from human eye-movement data can benefit modern NLP. Currently available Natural Language Processing (NLP) systems are weak AI systems: they seek to capture the functionality of human language processing, without worrying about how this processing is realized in human beings' hardware. In other words, these systems are oblivious to the actual cognitive processes involved in human language processing. This ignorance, however, is NOT bliss! The accuracy figures of all non-toy NLP systems saturate beyond a certain point, making it abundantly clear that "something different should be done."
|
| Subject
|
:
|
Eye tracking.
|
| Subject
|
:
|
Machine learning.
|
| Subject
|
:
|
Natural language processing (Computer science)
|
| Subject
|
:
|
COMPUTERS-- General.
|
| Subject
|
:
|
Eye tracking.
|
| Subject
|
:
|
Machine learning.
|
| Subject
|
:
|
Natural language processing (Computer science)
|
| Dewey Classification
|
:
|
006.3/5
|
| LC Classification
|
:
|
QA76.9.N38
|
| Added Entry
|
:
|
Bhattacharyya, Pushpak
|