Towards the Cognitive Informatics of Natural Language

2013 ◽  
Vol 7 (3) ◽  
pp. 25-45 ◽  
Author(s):  
J. M. Taylor ◽  
V. Raskin
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Cognitive Processes ◽  
Computational Analysis ◽  
Computer Experiment ◽  
Cognitive Computing ◽  
Cognitive Informatics ◽  
Cognitive Behaviors ◽  
Computational Humor ◽  
The Relationship

This paper deals with a contribution of computational analysis of verbal humor to natural language cognition. After a brief introduction to the growing area of computational humor and of its roots in humor theories, it describes and compares the results of a human-subject and computer experiment. The specific interest is to compare how well the computer, equipped with the resources and methodologies of the Ontological Semantic Technology, a comprehensive meaning access approach to natural language processing, can model several aspects of the cognitive behaviors of humans processing jokes from the Internet. The paper, sharing several important premises with cognitive informatics, is meant as a direct contribution to this rapidly developing transdisciplinary field, and as such, it bears on cognitive computing as well, especially at the level of implementation of computational humor in non-toy systems and the relationship to human cognitive processes of understanding and producing humor.

scholarly journals Getting in Shape: Word Embedding SubSpaces

2019 ◽  
Author(s):  
Tianyuan Zhou ◽  
João Sedoc ◽  
Jordan Rodu
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Semantic Similarity ◽  
Language Processing ◽  
Theoretical Framework ◽  
Word Embedding ◽  
Word Embeddings ◽  
Empirical Results ◽  
Linear Alignment ◽  
The Relationship

Many tasks in natural language processing require the alignment of word embeddings. Embedding alignment relies on the geometric properties of the manifold of word vectors. This paper focuses on supervised linear alignment and studies the relationship between the shape of the target embedding. We assess the performance of aligned word vectors on semantic similarity tasks and find that the isotropy of the target embedding is critical to the alignment. Furthermore, aligning with an isotropic noise can deliver satisfactory results. We provide a theoretical framework and guarantees which aid in the understanding of empirical results.

scholarly journals APMorph: finite-state transducer for Amazigh pronominal morphology

2021 ◽  
Vol 11 (1) ◽  
pp. 699
Author(s):  
Rachid Ammari ◽  
Ahbib Zenkoua
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Automatic Processing ◽  
Finite State ◽  
Finite State Transducer ◽  
The Relationship

Our work aims to present an amazigh pronominal morphological analyzer (APMorph) based on xerox’s finite-state transducer (XFST). Our system revolves around a large lexicon named “APlex” including the affixed pronoun to the noun and to the verb and the characteristics relating to each lemma. A set of rules are added to define the inflectional behavior and morphosyntactic links of each entry as well as the relationship between the different lexical units. The implementation and the evaluation of our approach will be detailed within this article. The use of XFST remains a relevant choice in the sense that this platform allows both analysis and generation. The robustness of our system makes it able to be integrated in other applications of natural language processing (NLP) especially spellchecking, machine translation, and machine learning. This paper presents a continuation of our previous works on the automatic processing of Amazigh nouns and verbs.

Are Atypical Things More Popular?

2018 ◽  
Vol 29 (7) ◽  
pp. 1178-1184 ◽  
Author(s):  
Jonah Berger ◽  
Grant Packard
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Cultural Dynamics ◽  
The Relationship ◽  
Shed Light

Why do some cultural items become popular? Although some researchers have argued that success is random, we suggest that how similar items are to each other plays an important role. Using natural language processing of thousands of songs, we examined the relationship between lyrical differentiation (i.e., atypicality) and song popularity. Results indicated that the more different a song’s lyrics are from its genre, the more popular it becomes. This relationship is weaker in genres where lyrics matter less (e.g., dance) or where differentiation matters less (e.g., pop) and occurs for lyrical topics but not style. The results shed light on cultural dynamics, why things become popular, and the psychological foundations of culture more broadly.

scholarly journals Assessing experienced tranquillity through natural language processing and landscape ecology measures

2021 ◽  
Author(s):  
Flurina M. Wartmann ◽  
Olga Koblet ◽  
Ross S. Purves
Keyword(s):  
Natural Language Processing ◽  
Land Cover ◽  
Natural Language ◽  
Language Processing ◽  
Landscape Planning ◽  
Text Data ◽  
Landscape Characteristics ◽  
Landscape Ecological ◽  
The Relationship ◽  
Negative Predictor

Abstract Context Identifying tranquil areas is important for landscape planning and policy-making. Research demonstrated discrepancies between modelled potential tranquil areas and where people experience tranquillity based on field surveys. Because surveys are resource-intensive, user-generated text data offers potential for extracting where people experience tranquillity. Objectives We explore and model the relationship between landscape ecological measures and experienced tranquillity extracted from user-generated text descriptions. Methods Georeferenced, user-generated landscape descriptions from Geograph.UK were filtered using keywords related to tranquillity. We stratify resulting tranquil locations according to dominant land cover and quantify the influence of landscape characteristics including diversity and naturalness on explaining the presence of tranquillity. Finally, we apply natural language processing to identify terms linked to tranquillity keywords and compare the similarity of these terms across land cover classes. Results Evaluation of potential keywords yielded six keywords associated with experienced tranquillity, resulting in 15,350 extracted tranquillity descriptions. The two most common land cover classes associated with tranquillity were arable and horticulture, and improved grassland, followed by urban and suburban. In the logistic regression model across all land cover classes, freshwater, elevation and naturalness were positive predictors of tranquillity. Built-up area was a negative predictor. Descriptions of tranquillity were most similar between improved grassland and arable and horticulture, and most dissimilar between arable and horticulture and urban. Conclusions This study highlights the potential of applying natural language processing to extract experienced tranquillity from text, and demonstrates links between landscape ecological measures and tranquillity as a perceived landscape quality.

scholarly journals SKOS concepts and natural language concepts: An analysis of latent relationships in KOSs

2016 ◽  
Vol 43 (4) ◽  
pp. 492-508 ◽  
Author(s):  
Anna Mastora ◽  
Manolis Peponakis ◽  
Sarantos Kapidakis
Keyword(s):  
Semantic Web ◽  
Natural Language ◽  
Language Processing ◽  
Main Concern ◽  
Uniform Resource Identifier ◽  
Lexical Representations ◽  
Knowledge Organisation ◽  
Subject Headings ◽  
Morphosyntactic Analysis ◽  
The Relationship

The vehicle to represent Knowledge Organisation Systems (KOSs) in the environment of the Semantic Web and linked data is the Simple Knowledge Organisation System (SKOS). SKOS provides a way to assign a Uniform Resource Identifier (URI) to each concept, and this URI functions as a surrogate for the concept. This fact makes of main concern the need to clarify the URIs’ ontological meaning. The aim of this study is to investigate the relationship between the ontological substance of KOS concepts and concepts revealed through the grammatical and syntactic formalisms of natural language. For this purpose, we examined the dividableness of concepts in specific KOSs (i.e. a thesaurus, a subject headings system and a classification scheme) by applying Natural Language Processing (NLP) techniques (i.e. morphosyntactic analysis) to the lexical representations (i.e. RDF literals) of SKOS concepts. The results of the comparative analysis reveal that, despite the use of multi-word units, thesauri tend to represent concepts in a way that can hardly be further divided conceptually, while subject headings and classification schemes – to a certain extent – comprise terms that can be decomposed into more conceptual constituents. Consequently, SKOS concepts deriving from thesauri are more likely to represent atomic conceptual units and thus be more appropriate tools for inference and reasoning. Since identifiers represent the meaning of a concept, complex concepts are neither the most appropriate nor the most efficient way of modelling a KOS for the Semantic Web.

scholarly journals Representation of Words in Natural Language Processing: A Survey

2019 ◽  
pp. 82-87
Author(s):  
Y. Losieva
Keyword(s):  
Neural Networks ◽  
Natural Language Processing ◽  
Natural Language ◽  
Computational Linguistics ◽  
Language Processing ◽  
Word Embeddings ◽  
Vector Representation ◽  
Advantages And Disadvantages ◽  
Word Representation ◽  
The Relationship

The article is devoted to research to the state-of-art vector representation of words in natural language processing. Three main types of vector representation of a word are described, namely: static word embeddings, use of deep neural networks for word representation and dynamic) word embeddings based on the context of the text. This is a very actual and much-demanded area in natural language processing, computational linguistics and artificial intelligence at all. Proposed to consider several different models for vector representation of the word (or word embeddings), from the simplest (as a representation of text that describes the occurrence of words within a document or learning the relationship between a pair of words) to the multilayered neural networks and deep bidirectional transformers for language understanding, are described chronologically in relation to the appearance of models. Improvements regarding previous models are described, both the advantages and disadvantages of the presented models and in which cases or tasks it is better to use one or another model.

scholarly journals Utterance and Objective: Issues in Natural Language Communication

AI Magazine ◽  
2017 ◽  
Vol 1 (1) ◽  
pp. 11 ◽  
Author(s):  
Barbara J. Grosz
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Computer Systems ◽  
Natural Languages ◽  
What Is Said ◽  
Language Communication ◽  
Natural Language Communication ◽  
The Relationship ◽  
Meaningful Sense

Two premises, reflected in the title, underlie the perspective from which I will consider research in natural language processing in this article. First, progress on building computer systems that process natural languages in any meaningful sense (i.e., systems that interact reasonably with people in natural language) requires considering language as part of a larger communicative situation. Second, as the phrase “utterance and objective” suggests, regarding language as communication requires consideration of what is said literally, what is intended, and the relationship between the two.

scholarly journals On the track of Artificial Intelligence: Learning with Intelligent Personal Assistants

2016 ◽  
Vol 13 (1) ◽  
pp. 592 ◽  
Author(s):  
Nil Goksel Canbek ◽  
Mehmet Emin Mutlu
Keyword(s):  
Artificial Intelligence ◽  
Natural Language Processing ◽  
Natural Language ◽  
Operating Systems ◽  
Language Processing ◽  
Digital Communication ◽  
Cognitive Computing ◽  
Computing Technologies ◽  
Personal Assistants ◽  
Potential Use

<p>In a technology dominated world, useful and timely information can be accessed quickly via Intelligent Personal Assistants (IPAs).  By the use of these assistants built into mobile operating systems, daily electronic tasks of a user can be accomplished 24/7. Such tasks like taking dictation, getting turn-by-turn directions, vocalizing email messages, reminding daily appointments, setting reminders, responding any factual questions and invoking apps can be completed by  IPAs such as Apple’s <a href="http://searchconsumerization.techtarget.com/definition/Siri" target="_blank">Siri</a>, <a href="http://whatis.techtarget.com/definition/Google-Now" target="_blank">Google Now</a> and Microsoft Cortana. The mentioned assistants programmed within Artificial Intelligence (AI) do create an interaction between human and computer through a natural language used in digital communication. In this regard, the overall purpose of this study is to examine the potential use of IPAs that use advanced cognitive computing technologies and Natural Language Processing (NLP) for learning. To achieve this purpose, the working system of IPAs is reviewed briefly within the scope of AI that has recently become smarter to predict, comprehend and carry out multi-step and complex requests of users.</p>

Understanding How We Produce Written Words

2019 ◽  
pp. 424-448
Author(s):  
Brenda Rapp ◽  
Jeremy Purcell
Keyword(s):  
Language Processing ◽  
Cognitive Processes ◽  
Language Production ◽  
Written Language ◽  
Current Understanding ◽  
Written Word ◽  
The Relationship ◽  
Cognitive Neuropsychological

Most of the current understanding of how we produce written language comes from psycholinguistic and cognitive neuropsychological investigations. More recently, both neuroimaging and lesion-based investigations have provided valuable information not only regarding the neural bases of the cognitive processes of written language production, but also regarding key cognitive processes and representations. This chapter focuses on contributions to current understanding of written word production that come from the study of the brain. Four fundamental issues of cognitive representation and processing in spelling are reviewed: the distinction between orthographic long-term and working-memory; the distinction between lexical and sublexical spelling processes; the relationship between reading and spelling; and the role of abstract letter representations in spelling. It specifically highlights the neural findings that have contributed significantly to current understanding of these issues. In some cases, the neural data provide convergence with behavioral findings; in others, they constitute unique contributions. The work reviewed here exemplifies the role of neurolinguistics evidence in furthering understanding of language processing and representation.

Semi-Automated Ontology building through Natural Language Processing

2014 ◽  
Vol 13 (8) ◽  
pp. 4738-4746
Author(s):  
Jaytrilok Choudhary ◽  
Deepak Singh Tomar
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Domain Knowledge ◽  
Experimental Result ◽  
Parts Of Speech ◽  
Domain Experts ◽  
Ontology Building ◽  
The Relationship ◽  
Natural Language Syntax ◽  
Fair Degree

Ontology is a backbone of semantic web which is used for domain knowledge representation. Ontology provides the platform for effective extraction of information. Usually, ontology is developed manually, but the manual ontology construction requires lots of efforts by domain experts. It is also time consuming and costly. Thus, an approach to build ontology in semi-automated manner has been proposed. The proposed approach extracts concept automatically from open directory Dmoz. The Stanford Parser is explored to parse natural language syntax and extract the parts of speech which are used to form the relationship among the concepts. The experimental result shows a fair degree of accuracy which may be improved in future with more sophisticated approach.

Sign in / Sign up

Export Citation Format

Share Document