1
Software Engineering / Re: SIGNS YOU NEED TO DEFINE SOFTWARE DEVELOPMENT PROCESS
« on: September 25, 2018, 06:50:27 PM »
Thanks for sharing. 
News:
Daffodil International University Forum contains information about Open Text material, which is only intended for the significant learning purposes of the university students, faculty, other members, and the knowledge seekers of the entire world and is hoped that the offerings will aide in the distribution of reliable information and data relating to the many areas of knowledge.
Show Posts
This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.
Pages: [1] 2
2
Software Engineering / Re: What is Design Pattern and why it's needed?
« on: September 25, 2018, 06:49:23 PM »
very informative
3
Natural Language Processing / 4 APPROACHES TO NATURAL LANGUAGE PROCESSING & UNDERSTANDING
« on: September 25, 2018, 06:47:39 PM »
In 1971, Terry Winograd wrote the SHRDLU program while completing his PhD at MIT. SHRDLU features a world of toy blocks where the computer translates human commands into physical actions, such as “move the red pyramid next to the blue cube.” To succeed in such tasks, the computer must build up semantic knowledge iteratively, a process Winograd discovered was brittle and limited.
The rise of chatbots and voice activated technologies has renewed fervor in natural language processing (NLP) and natural language understanding (NLU) techniques that can produce satisfying human-computer dialogs. Unfortunately, academic breakthroughs have not yet translated to improved user experiences, with Gizmodo writer Darren Orf declaring Messenger chatbots “frustrating and useless” and Facebook admitting a 70% failure rate for their highly anticipated conversational assistant M.
Nevertheless, researchers forge ahead with new plans of attack, occasionally revisiting the same tactics and principles Winograd tried in the 70s. OpenAI recently leveraged reinforcement learning to teach to agents to design their own language by “dropping them into a set of simple worlds, giving them the ability to communicate, and then giving them goals that can be best achieved by communicating with other agents.” The agents independently developed a simple “grounded” language.
MIT Media Lab presents this satisfying clarification on what “grounded” means in the context of language: “Language is grounded in experience. Unlike dictionaries which define words in terms of other words, humans understand many basic words in terms of associations with sensory-motor experiences. People must interact physically with their world to grasp the essence of words like “red,” “heavy,” and “above.” Abstract words are acquired only in relation to more concretely grounded terms. Grounding is thus a fundamental aspect of spoken language, which enables humans to acquire and to use words and sentences in context.”
The antithesis of grounded language is inferred language. Inferred language derives meaning from words themselves rather than what they represent. When trained only on large corpuses of text, but not on real-world representations, statistical methods for NLP and NLU lack true understanding of what words mean. OpenAI points out that such approaches share the weaknesses revealed by John Searle’s famous Chinese Room thought experiment. Equipped with a universal dictionary to map all possible Chinese input sentences to Chinese output sentences, anyone can perform a brute force lookup and produce conversationally acceptable answers without understanding what they’re actually saying.
LANGUAGE COMPLEXITY INSPIRES MANY NATURAL LANGUAGE PROCESSING (NLP) TECHNIQUES
Percy Liang, a Stanford CS professor and NLP expert, breaks down the various approaches to NLP / NLU into four distinct categories:
1) Distributional
2) Frame-based
3) Model-theoretical
4) Interactive learning
You might appreciate a brief linguistics lesson before we continue on to define and describe those categories. There are three levels of linguistic analysis:
1) Syntax – what is grammatical?
2) Semantics – what is the meaning?
3) Pragmatics – what is the purpose or goal?
Source: https://www.topbots.com/4-different-approaches-natural-language-processing-understanding/
The rise of chatbots and voice activated technologies has renewed fervor in natural language processing (NLP) and natural language understanding (NLU) techniques that can produce satisfying human-computer dialogs. Unfortunately, academic breakthroughs have not yet translated to improved user experiences, with Gizmodo writer Darren Orf declaring Messenger chatbots “frustrating and useless” and Facebook admitting a 70% failure rate for their highly anticipated conversational assistant M.
Nevertheless, researchers forge ahead with new plans of attack, occasionally revisiting the same tactics and principles Winograd tried in the 70s. OpenAI recently leveraged reinforcement learning to teach to agents to design their own language by “dropping them into a set of simple worlds, giving them the ability to communicate, and then giving them goals that can be best achieved by communicating with other agents.” The agents independently developed a simple “grounded” language.
MIT Media Lab presents this satisfying clarification on what “grounded” means in the context of language: “Language is grounded in experience. Unlike dictionaries which define words in terms of other words, humans understand many basic words in terms of associations with sensory-motor experiences. People must interact physically with their world to grasp the essence of words like “red,” “heavy,” and “above.” Abstract words are acquired only in relation to more concretely grounded terms. Grounding is thus a fundamental aspect of spoken language, which enables humans to acquire and to use words and sentences in context.”
The antithesis of grounded language is inferred language. Inferred language derives meaning from words themselves rather than what they represent. When trained only on large corpuses of text, but not on real-world representations, statistical methods for NLP and NLU lack true understanding of what words mean. OpenAI points out that such approaches share the weaknesses revealed by John Searle’s famous Chinese Room thought experiment. Equipped with a universal dictionary to map all possible Chinese input sentences to Chinese output sentences, anyone can perform a brute force lookup and produce conversationally acceptable answers without understanding what they’re actually saying.
LANGUAGE COMPLEXITY INSPIRES MANY NATURAL LANGUAGE PROCESSING (NLP) TECHNIQUES
Percy Liang, a Stanford CS professor and NLP expert, breaks down the various approaches to NLP / NLU into four distinct categories:
1) Distributional
2) Frame-based
3) Model-theoretical
4) Interactive learning
You might appreciate a brief linguistics lesson before we continue on to define and describe those categories. There are three levels of linguistic analysis:
1) Syntax – what is grammatical?
2) Semantics – what is the meaning?
3) Pragmatics – what is the purpose or goal?
Source: https://www.topbots.com/4-different-approaches-natural-language-processing-understanding/
4
Software Engineering / Re: Harvard Printer Blasts Droplets with 100 Times Earth's Gravitational Force
« on: September 25, 2018, 06:41:55 PM »
Very informative
5
Software Engineering / What is Numerical Analysis
« on: September 16, 2018, 03:31:10 PM »
Numerical analysis, area of mathematics and computer science that creates, analyzes, and implements algorithms for obtaining numerical solutions to problems involving continuous variables. Such problems arise throughout the natural sciences, social sciences, engineering, medicine, and business. Since the mid 20th century, the growth in power and availability of digital computers has led to an increasing use of realistic mathematical models in science and engineering, and numerical analysis of increasing sophistication is needed to solve these more detailed models of the world. The formal academic area of numerical analysis ranges from quite theoretical mathematical studies to computer science issues.
With the increasing availability of computers, the new discipline of scientific computing, or computational science, emerged during the 1980s and 1990s. The discipline combines numerical analysis, symbolic mathematical computations, computer graphics, and other areas of computer science to make it easier to set up, solve, and interpret complicated mathematical models of the real world.
Source: https://www.britannica.com/science/numerical-analysis
With the increasing availability of computers, the new discipline of scientific computing, or computational science, emerged during the 1980s and 1990s. The discipline combines numerical analysis, symbolic mathematical computations, computer graphics, and other areas of computer science to make it easier to set up, solve, and interpret complicated mathematical models of the real world.
Source: https://www.britannica.com/science/numerical-analysis
6
Software Engineering / Re: No Vision, No Problem for This 'Blind' Cheetah Robot
« on: September 16, 2018, 11:44:32 AM »
Thanks for sharing
7
Machine Learning/ Deep Learning / Supervised vs. Unsupervised Machine Learning
« on: September 16, 2018, 11:38:32 AM »
Data scientists use many different kinds of machine learning algorithms to discover patterns in big data that lead to actionable insights. At a high level, these different algorithms can be classified into two groups based on the way they “learn” about data to make predictions: supervised and unsupervised learning.
Supervised machine learning is the more commonly used between the two. It includes such algorithms as linear and logistic regression, multi-class classification, and support vector machines. Supervised learning is so named because the data scientist acts as a guide to teach the algorithm what conclusions it should come up with. It’s similar to the way a child might learn arithmetic from a teacher. Supervised learning requires that the algorithm’s possible outputs are already known and that the data used to train the algorithm is already labeled with correct answers. For example, a classification algorithm will learn to identify animals after being trained on a dataset of images that are properly labeled with the species of the animal and some identifying characteristics.
On the other hand, unsupervised machine learning is more closely aligned with what some call true artificial intelligence — the idea that a computer can learn to identify complex processes and patterns without a human to provide guidance along the way. Although unsupervised learning is prohibitively complex for some simpler enterprise use cases, it opens the doors to solving problems that humans normally would not tackle. Some examples of unsupervised machine learning algorithms include k-means clustering, principal and independent component analysis, and association rules.
While a supervised classification algorithm learns to ascribe inputted labels to images of animals, its unsupervised counterpart will look at inherent similarities between the images and separate them into groups accordingly, assigning its own new label to each group. In a practical example, this type of algorithm is useful for customer segmentation because it will return groups based on parameters that a human may not consider due to pre-existing biases about the company’s demographic.
Choosing to use either a supervised or unsupervised machine learning algorithm typically depends on factors related to the structure and volume of your data and the use case of the issue at hand. A well-rounded data science program will use both types of algorithms to build predictive data models that help stakeholders make decisions across a variety of business challenges.
Source: https://www.datascience.com/blog/supervised-and-unsupervised-machine-learning-algorithms
Supervised machine learning is the more commonly used between the two. It includes such algorithms as linear and logistic regression, multi-class classification, and support vector machines. Supervised learning is so named because the data scientist acts as a guide to teach the algorithm what conclusions it should come up with. It’s similar to the way a child might learn arithmetic from a teacher. Supervised learning requires that the algorithm’s possible outputs are already known and that the data used to train the algorithm is already labeled with correct answers. For example, a classification algorithm will learn to identify animals after being trained on a dataset of images that are properly labeled with the species of the animal and some identifying characteristics.
On the other hand, unsupervised machine learning is more closely aligned with what some call true artificial intelligence — the idea that a computer can learn to identify complex processes and patterns without a human to provide guidance along the way. Although unsupervised learning is prohibitively complex for some simpler enterprise use cases, it opens the doors to solving problems that humans normally would not tackle. Some examples of unsupervised machine learning algorithms include k-means clustering, principal and independent component analysis, and association rules.
While a supervised classification algorithm learns to ascribe inputted labels to images of animals, its unsupervised counterpart will look at inherent similarities between the images and separate them into groups accordingly, assigning its own new label to each group. In a practical example, this type of algorithm is useful for customer segmentation because it will return groups based on parameters that a human may not consider due to pre-existing biases about the company’s demographic.
Choosing to use either a supervised or unsupervised machine learning algorithm typically depends on factors related to the structure and volume of your data and the use case of the issue at hand. A well-rounded data science program will use both types of algorithms to build predictive data models that help stakeholders make decisions across a variety of business challenges.
Source: https://www.datascience.com/blog/supervised-and-unsupervised-machine-learning-algorithms
8
Natural Language Processing / Re: NLP: What it is and why it matters
« on: September 16, 2018, 11:34:44 AM »
Thanks for sharing
9
Software Engineering / WHY DO WE HAVE TO STUDY NUMERICAL ANALYSIS?
« on: September 16, 2018, 10:50:59 AM »
In the teaching of mathematics in engineering careers, the importance and usefulness of the different issues studied must be emphasized to capture the interest of students. The discussion of theory within the context of problem solving, not only motivates students but also helps them to achieve significant and comprehensive learning. This methodology may be useful to solve the disruption between mathematics and specialty subjects.
Some experiences have been carried out in Numerical Analysis courses at Facultad Regional San Nicolás, Universidad Tecnológica Nacional in Argentina. A great motivation in students has been observed when working with visual applications dealing with different issues in the subject, designed using different Computer Algebra Systems (CAS).
With the aim that students achieve meaningful learning, it was decided to include problems where numerical methods are necessary to obtain their solution. So as students can focus on the problems and the solution techniques needed, without wasting time making calculations, some apps were designed to be used for solving them.
The newest applications were designed with Mathematica, as computable document format files (CDF). The program required to open these files is the CDF-Player, available for free in the Wolfram´s website. Also, this kind of files may be embedded in a webpage, and they can be executed in a web browser if the corresponding plugin is installed. In this way, students can access to the CDF files almost everywhere.
Source: https://library.iated.org/view/CALIGARIS2016STU
Some experiences have been carried out in Numerical Analysis courses at Facultad Regional San Nicolás, Universidad Tecnológica Nacional in Argentina. A great motivation in students has been observed when working with visual applications dealing with different issues in the subject, designed using different Computer Algebra Systems (CAS).
With the aim that students achieve meaningful learning, it was decided to include problems where numerical methods are necessary to obtain their solution. So as students can focus on the problems and the solution techniques needed, without wasting time making calculations, some apps were designed to be used for solving them.
The newest applications were designed with Mathematica, as computable document format files (CDF). The program required to open these files is the CDF-Player, available for free in the Wolfram´s website. Also, this kind of files may be embedded in a webpage, and they can be executed in a web browser if the corresponding plugin is installed. In this way, students can access to the CDF files almost everywhere.
Source: https://library.iated.org/view/CALIGARIS2016STU
10
Software Engineering / Nasa names astronauts for first commercial flights
« on: August 05, 2018, 10:46:25 AM »
Nasa has named the astronauts who will fly the first missions into space on commercially provided rockets and capsules, starting next year.
The nine individuals will go up on systems developed by - and contracted from - the Boeing and SpaceX firms.
Most have previous experience in orbit. Among them are the commander and pilot of the final shuttle mission in 2011.
For the past seven years, Russian rockets have been the only way to get people into orbit.
Nasa Administrator Jim Bridenstine introduced the astronauts during a ceremony at the Johnson Space Center in Houston, Texas.
"For the first time since 2011, we are on the brink of launching American astronauts on American rockets from American soil," he told the enthusiastic audience.
The commander on the historic last shuttle mission, Chris Ferguson, is now a Boeing employee and has been heavily involved in developing the company's CST-100 Starliner capsule.
When this ship makes its maiden crewed flight in the middle of next year, launching atop an Atlas rocket from Cape Canaveral, Ferguson will be joined by Eric Boe and Nicole Aunapu Mann.
Boe is a former shuttle pilot; Mann will be making her first trip into space.
The SpaceX Dragon capsule, on current timelines, is set to make its maiden crewed flight in April. It will ride atop a Falcon-9 rocket from the Kennedy Space Center. It will actually use one of the old shuttle pads, although this has now been modified for the smaller Falcon.
At the helm will be Doug Hurley and Bob Behnken. Hurley was the pilot on the last shuttle mission. Behnken has been in space on two previous occasions.
The initial crewed flights by Boeing and SpaceX will spend a short period in orbit - measured perhaps in days or a few weeks, and attached to the International Space Station (ISS) - before coming back to Earth.
It is on later missions that the crew capsules will go to the station and dock for more extended stays, and Nasa also named the astronauts for those first flights as well.
For Boeing, this introductory long-duration mission includes Josh Cassada, who has never been in space before, and Suni Williams, who is one of the most experienced American astronauts in history, having spent a cumulative 321 days in orbit through her career.
For SpaceX, such an ISS mission would involve Victor Glover, another newbie, and Mike Hopkins, who has already spent 166 days on the sky-high lab during two tours of duty.
Nasa took the decision after the shuttle retired to turn transportation to low-Earth obit destinations into a service that it could buy. It has given seed money to SpaceX and Boeing to incentivise them, but the companies themselves have also had to invest their own money.
Nasa's motivation was to save money it could then spend on a rocket and capsule system to take humans back to the Moon and on to Mars.
That system will likely fly some time early next decade.
Source link: https://www.bbc.com/news/science-environment-45060553
The nine individuals will go up on systems developed by - and contracted from - the Boeing and SpaceX firms.
Most have previous experience in orbit. Among them are the commander and pilot of the final shuttle mission in 2011.
For the past seven years, Russian rockets have been the only way to get people into orbit.
Nasa Administrator Jim Bridenstine introduced the astronauts during a ceremony at the Johnson Space Center in Houston, Texas.
"For the first time since 2011, we are on the brink of launching American astronauts on American rockets from American soil," he told the enthusiastic audience.
The commander on the historic last shuttle mission, Chris Ferguson, is now a Boeing employee and has been heavily involved in developing the company's CST-100 Starliner capsule.
When this ship makes its maiden crewed flight in the middle of next year, launching atop an Atlas rocket from Cape Canaveral, Ferguson will be joined by Eric Boe and Nicole Aunapu Mann.
Boe is a former shuttle pilot; Mann will be making her first trip into space.
The SpaceX Dragon capsule, on current timelines, is set to make its maiden crewed flight in April. It will ride atop a Falcon-9 rocket from the Kennedy Space Center. It will actually use one of the old shuttle pads, although this has now been modified for the smaller Falcon.
At the helm will be Doug Hurley and Bob Behnken. Hurley was the pilot on the last shuttle mission. Behnken has been in space on two previous occasions.
The initial crewed flights by Boeing and SpaceX will spend a short period in orbit - measured perhaps in days or a few weeks, and attached to the International Space Station (ISS) - before coming back to Earth.
It is on later missions that the crew capsules will go to the station and dock for more extended stays, and Nasa also named the astronauts for those first flights as well.
For Boeing, this introductory long-duration mission includes Josh Cassada, who has never been in space before, and Suni Williams, who is one of the most experienced American astronauts in history, having spent a cumulative 321 days in orbit through her career.
For SpaceX, such an ISS mission would involve Victor Glover, another newbie, and Mike Hopkins, who has already spent 166 days on the sky-high lab during two tours of duty.
Nasa took the decision after the shuttle retired to turn transportation to low-Earth obit destinations into a service that it could buy. It has given seed money to SpaceX and Boeing to incentivise them, but the companies themselves have also had to invest their own money.
Nasa's motivation was to save money it could then spend on a rocket and capsule system to take humans back to the Moon and on to Mars.
That system will likely fly some time early next decade.
Source link: https://www.bbc.com/news/science-environment-45060553
11
Software Engineering / Discrete Mathematics Applications and Importance in Computer Science
« on: August 05, 2018, 10:20:20 AM »
Discrete mathematics is the branch of mathematics dealing with objects that can assume only distinct, separated values. The term "Discrete Mathematics" is therefore used in contrast with "Continuous Mathematics," which is the branch of mathematics dealing with objects that can vary smoothly (and which includes, for example, calculus). Whereas discrete objects can often be characterized by integers, continuous objects require real numbers.
The study of how discrete objects combine with one another and the probabilities of various outcomes is known as combinatorics. Other fields of mathematics that are considered to be part of discrete mathematics include graph theory and the theory of computation. Topics in number theory such as congruence’s and recurrence relations are also considered part of discrete mathematics.
The study of topics in discrete mathematics usually includes the study of algorithms, their implementations, and efficiencies. Discrete mathematics is the mathematical language of computer science, and as such, its importance has increased dramatically in recent decades.
The set of objects studied in discrete mathematics can be finite or infinite. The term finite mathematics is sometimes applied to parts of the field of discrete mathematics that deals with finite sets, particularly those areas relevant to business.
Research in discrete mathematics increased in the latter half of the twentieth century partly due to the development of digital computers which operate in discrete steps and store data in discrete bits. Concepts and notations from discrete mathematics are useful in studying and describing objects and problems in branches of computer science, such as computer algorithms, programming languages, cryptography, automated theorem proving, and software development. Conversely, computer implementations are significant in applying ideas from discrete mathematics to real-world problems, such as in operations research.
IMPORTANCE OF DISCRETE MATHEMATICS IN COMPUTER SCIENCE
Achieving working knowledge of many principles of computer science requires mastery of certain relevant mathematical concepts and skills. For example, A grasp of Boolean algebra including DeMorgans Law is useful for understanding Boolean expressions and the basics of combinational circuits concepts surrounding the growth of functions and summations are useful for analysis of loop control structures exposure to solving recurrence relations is de rigeur for the analysis of recursive algorithms and an introduction to proof methods facilitates consideration of program correctness and thinking rigorously in general.
Students are introduced to proof techniques before they begin to consider the idea of proving programs correct. They learn about propositional logic and Boolean algebra before they study some very elementary circuits and learn decision control structures and Boolean variables. They are introduced to predicate logic near the time they are beginning programming and learning about variables. They learn about growth of functions big-O notation and summations before they analyze loops and nested loops and they have the tools to begin algorithm analysis from the time they first begin to learn about iterative constructs. In conjunction with an introduction to number theory they do laboratory and programming exercises involving an assortment of integer algorithms.
Students learn about recursive definitions recurrence relations, analyzing recursive algorithms and writing recursive algorithms and programs together in the same course. They study matrices and matrix manipulations in conjunction with the array data structure. They learn about permutations and combinations, relations, graphs, and trees at the same time that their programming knowledge and sophistication are improving and they can do increasingly interesting programming exercises involving these concepts.
Source link: http://cybercomputing.blogspot.com/2012/06/discrete-mathematics-applications-and.html
The study of how discrete objects combine with one another and the probabilities of various outcomes is known as combinatorics. Other fields of mathematics that are considered to be part of discrete mathematics include graph theory and the theory of computation. Topics in number theory such as congruence’s and recurrence relations are also considered part of discrete mathematics.
The study of topics in discrete mathematics usually includes the study of algorithms, their implementations, and efficiencies. Discrete mathematics is the mathematical language of computer science, and as such, its importance has increased dramatically in recent decades.
The set of objects studied in discrete mathematics can be finite or infinite. The term finite mathematics is sometimes applied to parts of the field of discrete mathematics that deals with finite sets, particularly those areas relevant to business.
Research in discrete mathematics increased in the latter half of the twentieth century partly due to the development of digital computers which operate in discrete steps and store data in discrete bits. Concepts and notations from discrete mathematics are useful in studying and describing objects and problems in branches of computer science, such as computer algorithms, programming languages, cryptography, automated theorem proving, and software development. Conversely, computer implementations are significant in applying ideas from discrete mathematics to real-world problems, such as in operations research.
IMPORTANCE OF DISCRETE MATHEMATICS IN COMPUTER SCIENCE
Achieving working knowledge of many principles of computer science requires mastery of certain relevant mathematical concepts and skills. For example, A grasp of Boolean algebra including DeMorgans Law is useful for understanding Boolean expressions and the basics of combinational circuits concepts surrounding the growth of functions and summations are useful for analysis of loop control structures exposure to solving recurrence relations is de rigeur for the analysis of recursive algorithms and an introduction to proof methods facilitates consideration of program correctness and thinking rigorously in general.
Students are introduced to proof techniques before they begin to consider the idea of proving programs correct. They learn about propositional logic and Boolean algebra before they study some very elementary circuits and learn decision control structures and Boolean variables. They are introduced to predicate logic near the time they are beginning programming and learning about variables. They learn about growth of functions big-O notation and summations before they analyze loops and nested loops and they have the tools to begin algorithm analysis from the time they first begin to learn about iterative constructs. In conjunction with an introduction to number theory they do laboratory and programming exercises involving an assortment of integer algorithms.
Students learn about recursive definitions recurrence relations, analyzing recursive algorithms and writing recursive algorithms and programs together in the same course. They study matrices and matrix manipulations in conjunction with the array data structure. They learn about permutations and combinations, relations, graphs, and trees at the same time that their programming knowledge and sophistication are improving and they can do increasingly interesting programming exercises involving these concepts.
Source link: http://cybercomputing.blogspot.com/2012/06/discrete-mathematics-applications-and.html
12
Natural Language Processing / Re: Evaluation of Sentiment Classification
« on: August 05, 2018, 10:09:23 AM »
Thanks for sharing
13
Natural Language Processing / A Systematic Literature Review on Spell Checkers for Bangla Language
« on: July 26, 2018, 02:02:57 PM »
Abstract: Spell checkers check whether a word is
misspelled and provide suggestions to correct it.
Detection and correction of spelling errors in Bangla
language which is the seventh most spoken native
language in the world, is very onerous because of the
complex rules of Bangla spelling. There is no systematic
literature review on this research topic. In this paper, we
present a systematic literature review on checking and
correcting spelling errors in Bangla language. We
investigate the current methods used for spell checking
and find out what challenges are addressed by those
methods. We also report the limitations of those methods.
Recent relevant studies are selected based on a set of
significant criteria. Our results indicate that there are
research gaps in this research topic and has a potential for
further investigation
Full paper link: http://www.mecs-press.org/ijmecs/ijmecs-v9-n6/IJMECS-V9-N6-6.pdf
misspelled and provide suggestions to correct it.
Detection and correction of spelling errors in Bangla
language which is the seventh most spoken native
language in the world, is very onerous because of the
complex rules of Bangla spelling. There is no systematic
literature review on this research topic. In this paper, we
present a systematic literature review on checking and
correcting spelling errors in Bangla language. We
investigate the current methods used for spell checking
and find out what challenges are addressed by those
methods. We also report the limitations of those methods.
Recent relevant studies are selected based on a set of
significant criteria. Our results indicate that there are
research gaps in this research topic and has a potential for
further investigation
Full paper link: http://www.mecs-press.org/ijmecs/ijmecs-v9-n6/IJMECS-V9-N6-6.pdf
14
Natural Language Processing / Applications of Natural Language Processing
« on: July 18, 2018, 04:15:22 PM »
Natural language processing or NLP is a branch of artificial intelligence that has many important implications on the ways that computers and humans interact. Human language, developed over thousands and thousands of years, has become a nuanced form of communication that carries a wealth of information that often transcends the words alone. NLP will become an important technology in bridging the gap between human communication and digital data. Here are 5 ways that natural language processing will be used in the years to come.
1. Machine Translation
2. Fighting Spam
3. Information Extraction
4. Summarization
5. Question Answering
Source Link: https://www.lifewire.com/applications-of-natural-language-processing-technology-2495544
1. Machine Translation
2. Fighting Spam
3. Information Extraction
4. Summarization
5. Question Answering
Source Link: https://www.lifewire.com/applications-of-natural-language-processing-technology-2495544
15
Software Engineering / Re: বনশ্রীর এটিএমে মিলছে বিনামূল্যে পানি
« on: July 18, 2018, 04:11:08 PM »
Nice
Pages: [1] 2