An inductive method with genetic algorithm for learning phrase-structure-rule of natural language

1996 ◽  
Vol 1 (3-4) ◽  
pp. 640-644 ◽  
Author(s):  
Houfeng Wang ◽  
Dawei Dai
Keyword(s):  
Genetic Algorithm ◽  
Natural Language ◽  
Phrase Structure ◽  
Inductive Method

Design of GA and Ontology based NLP Frameworks for Online Opinion Mining

2019 ◽  
Vol 13 (2) ◽  
pp. 159-165
Author(s):  
Manik Sharma ◽  
Gurvinder Singh ◽  
Rajinder Singh
Keyword(s):  
Genetic Algorithm ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Opinion Mining ◽  
Hybrid Genetic Algorithm ◽  
Online Reviews ◽  
Middle Tier ◽  
Complete Set ◽  
Mining Model

Background: For almost every domain, a tremendous degree of data is accessible in an online and offline mode. Billions of users are daily posting their views or opinions by using different online applications like WhatsApp, Facebook, Twitter, Blogs, Instagram etc. Objective: These reviews are constructive for the progress of the venture, civilization, state and even nation. However, this momentous amount of information is useful only if it is collectively and effectively mined. Methodology: Opinion mining is used to extract the thoughts, expression, emotions, critics, appraisal from the data posted by different persons. It is one of the prevailing research techniques that coalesce and employ the features from natural language processing. Here, an amalgamated approach has been employed to mine online reviews. Results: To improve the results of genetic algorithm based opining mining patent, here, a hybrid genetic algorithm and ontology based 3-tier natural language processing framework named GAO_NLP_OM has been designed. First tier is used for preprocessing and corrosion of the sentences. Middle tier is composed of genetic algorithm based searching module, ontology for English sentences, base words for the review, complete set of English words with item and their features. Genetic algorithm is used to expedite the polarity mining process. The last tier is liable for semantic, discourse and feature summarization. Furthermore, the use of ontology assists in progressing more accurate opinion mining model. Conclusion: GAO_NLP_OM is supposed to improve the performance of genetic algorithm based opinion mining patent. The amalgamation of genetic algorithm, ontology and natural language processing seems to produce fast and more precise results. The proposed framework is able to mine simple as well as compound sentences. However, affirmative preceded interrogative, hidden feature and mixed language sentences still be a challenge for the proposed framework.

Iconicity in syntax and the architecture of linguistic theory

2020 ◽  
Vol 44 (1) ◽  
pp. 95-131
Author(s):  
Diego Gabriel Krivochen ◽  
Ľudmila Lacková
Keyword(s):  
Natural Language ◽  
Linear Order ◽  
Phrase Structure ◽  
Linguistic Theory ◽  
Sound Symbolism ◽  
Inherent Structure ◽  
Ancient Times ◽  
Generative System

Abstract Linguistic iconicity has been studied since ancient times (e.g., Plato’s Cratylus, see Cooper & Hutchinson 1997). Within modern grammatical description, this notion was mostly developed by Jakobson and Benveniste; nowadays, iconicity in language is even being experimentally tested (e.g., Blasi et al. 2016; Diatka & Milička 2017). However, most studies on linguistic iconicity pertain to prosody, sound symbolism, or morphology; syntactic iconicity has been vastly underexplored. In this paper, we present two hypotheses concerning syntactic iconicity: (1) syntactic descriptions of natural language strings have an inherent structure which is isomorphic to that of representations in some other component of grammar or a non-grammatical system; or (2) linear order imposed on phrase structure is isomorphic to that in some other component of grammar or a non-grammatical system. We will argue in favour of the former, which constitutes a novel perspective on iconicity in grammar. We furthermore discuss the place that iconicity may have in the architecture of a generative system.

Fuzzy Linguistic Summarization with Genetic Algorithm: An Application with Operational and Financial Healthcare Data

2017 ◽  
Vol 25 (04) ◽  
pp. 599-620 ◽  
Author(s):  
Tunahan Altintop ◽  
Ronald R. Yager ◽  
Diyar Akay ◽  
Fatih Emre Boran ◽  
Muhammet Ünal
Keyword(s):  
Genetic Algorithm ◽  
Natural Language ◽  
Real Data ◽  
Threshold Value ◽  
Healthcare Services ◽  
Vital Role ◽  
Healthcare Data ◽  
Medical Healthcare ◽  
Fuzzy Linguistic ◽  
First Time

It is now well recognized that knowledge extracted from rich healthcare data play a vital role for delivery, management and planning of healthcare services. So far, however, there is not much study done on the domain of operational and financial healthcare data since, up to now, a great deal of works are dedicated to clinical/medical healthcare data for the purposes of diagnosis and treatment of diseases. In this paper, an attempt is made, by applying fuzzy linguistic summarization, for the first time to discover knowledge from operational and financial healthcare data. Fuzzy linguistic summarization, in its simplest term, provides natural language based summaries from a dataset in a human consistent way along with a degree of truth attached to each summary. While basically valuable, its benefit can be increased by only generating summaries with a degree of truth above than an indicated threshold value. A genetic algorithm is developed within this context in order to eliminate less promising and useless linguistic summaries. We assess the proposed approach experimentally on a real data and evaluate the generated summaries to gain actionable insights from them.

Mixed computation

2021 ◽  
Vol 3 (2) ◽  
pp. 215-244
Author(s):  
Diego Gabriel Krivochen
Keyword(s):  
Computational Complexity ◽  
Natural Language ◽  
Phrase Structure ◽  
Explicit Characterization ◽  
Tree Adjoining Grammar ◽  
Branching Trees ◽  
Structural Descriptions ◽  
Context Free ◽  
The Way

Abstract Proof-theoretic models of grammar are based on the view that an explicit characterization of a language comes in the form of the recursive enumeration of strings in that language. That recursive enumeration is carried out by a procedure which strongly generates a set of structural descriptions Σ and weakly generates a set of strings S; a grammar is thus a function that pairs an element of Σ with elements of S. Structural descriptions are obtained by means of Context-Free phrase structure rules or via recursive combinatorics and structure is assumed to be uniform: binary branching trees all the way down. In this work we will analyse natural language constructions for which such a rigid conception of phrase structure is descriptively inadequate and propose a solution for the problem of phrase structure grammars assigning too much or too little structure to natural language strings: we propose that the grammar can oscillate between levels of computational complexity in local domains, which correspond to elementary trees in a lexicalised Tree Adjoining Grammar.

On syntactic categories

1981 ◽  
Vol 295 (1077) ◽  
pp. 267-283 ◽  
Keyword(s):  
Natural Language ◽  
General Type ◽  
Phrase Structure ◽  
Negative Answer ◽  
Syntactic Category ◽  
Quarter Century ◽  
Context Free

A traditional concern of grammarians has been the question of whether the members of given pairs of expressions belong to the same or different syntactic categories. Consider the following example sentences. ( a ) I think Fido destroyed the kennel . ( b ) The kennel, I think Fido destroyed . Are the two underlined expressions members of the same syntactic category or not? The generative grammarians of the last quarter century have, almost without exception, taken the answer to be affirmative. In the present paper I explore the implications of taking the answer to be negative. The changes consequent upon this negative answer turn out to be very far-reaching: (i) it becomes as simple to state rules for constructions of the general type exemplified in ( b ) as it is for the canonical NP VP construction in ( a ); (ii) we immediately derive an explanation for a range of coordination facts that have remained quite mysterious since they were discovered by J. R. Ross some 15 years ago; (iii) our grammars can entirely dispense with the class of rules known as transformations; (iv) our grammars can be shown to be formally equivalent to what are known as the context-free phrase structure grammars; (v) this latter consequence has the effect of making potentially relevant to natural language grammars a whole literature of mathematical results on the parsability and learnability of context-free phrase structure grammars.

scholarly journals Generating Creative Language - Theories, Practice and Evaluation

2020 ◽  
Author(s):  
Mika Hämäläinen
Keyword(s):  
Genetic Algorithm ◽  
Natural Language ◽  
Ad Hoc ◽  
Theoretical Perspective ◽  
Theoretical Work ◽  
Computational Creativity ◽  
Practical Solution ◽  
Language Generation ◽  
Communicative Context ◽  
Creative Language

This thesis presents approaches to computationally creative natural language generation focusing on theoretical foundations, practical solutions and evaluation. I defend that a theoretical definition is crucial for computational creativity and that the practical solution must closely follow the theoretical definition. Finally, evaluation must be based on the underlying theory and what was actually modelled in the practical solution. A theoretical void in the existing theoretical work on computational creativity is identified. The existing theories do not explicitly take into account the communicative nature of natural language. Therefore, a new theoretical framework is elaborated that identifies how computational creativity can take place in a setting that has a clear communicative goal. This introduces a communicative-creative trade off that sets limits to creativity in such a communicative context. My framework divides creativity in three categories: message creativity, contextual creativity and communicative creativity. Any computationally creative NLG approach not taking communicativity into account is called mere surface generation.I propose a novel master-apprentice approach for creative language generation. The approach consists of a genetic algorithm, the fitness functions of which correspond to different parameters defined as important for the creative task in question from a theoretical perspective. The output of the genetic algorithm together with possible human authored data are used to train the apprentice, which is a sequence-to-sequence neural network model. The role of the apprentice in the system is to approximate creative autonomy.Evaluation is approached from three different perspectives in this work: ad-hoc and abstract, theory-based and abstract, and theory-based and concrete. The first perspective is the most common one in the current literature and its shortcomings are demonstrated and discussed. This starts a gradual shift towards more meaningful evaluation by first using proper theories to define the task being modelled and finally reducing the room for subjective interpretation by suggesting the use of concrete evaluation questions.

scholarly journals Towards Adversarial Genetic Text Generation

2021 ◽  
Author(s):  
Deniz Kavi
Keyword(s):  
Genetic Algorithm ◽  
Natural Language ◽  
Language Processing ◽  
Text Classification ◽  
Future Research ◽  
Grading System ◽  
Text Generation ◽  
Recent Success ◽  
Clustering Model ◽  
Better Than

Text generation is the task of generating natural language, and producing outputs similar to or better than human texts. Due to deep learning’s recent success in the field of natural language processing, computer generated text has come closer to becoming indistinguishable to human writing. Genetic Algorithms have not been as popular in the field of text generation. We propose a genetic algorithm combined with text classification and clustering models which automatically grade the texts generated by the genetic algorithm. The genetic algorithm is given poorly generated texts from a Markov chain, these texts are then graded by a text classifier and a text clustering model. We then apply crossover to pairs of texts, with emphasis on those that received higher grades. Changes to the grading system and further improvements to the genetic algorithm are to be the focus of future research.

Sign in / Sign up

Export Citation Format

Share Document