@Article{saini2020ccs,
  author   = {S. {Saini} and V. {Sahula}},
  doi      = {10.1049/ccs.2019.0017},
  journal  = {IET Cognitive Computation and Systems},
  number   = {1},
  title    = {Cognitive architecture for natural language comprehension},
  url      = {https://ieeexplore.ieee.org/document/9037560},
  volume   = {2},
  year     = {2020},
  issn     = {2517-7567},
  pages    = {23-31},
  abstract = {Human interactions with computers in natural language have always been a challenging task. Numerous computational systems are being designed to bring this interaction as close to the natural language commands as possible. Cognitive architectures are worthy solutions to solve this problem. In the present work, the authors have developed a cognitive architecture, which is capable of learning using natural language input. It can learn with minimal input data and has been designed using neural networks. The system is inspired by conventional cognitive models for working memory. They have proposed the system with a central executive unit controlling the short-term memory and long-term memory to comprehend the text input given as a natural language command and generate the output in natural language. The system comprises a feedback system as well to improve the learning process. The model has been trained using 1000 English sentences taught to primary school students. The system is capable of comprehending the relations between words, verbs, nouns, pronouns, adjectives, and generates logical reasoning-based answers.},
  file     = {:https\://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9037560:},
  keywords = {neural nets;natural language processing;computer aided instruction;natural languages;cognition;learning (artificial intelligence);cognitive systems;inference mechanisms;cognitive architecture;natural language comprehension;human interactions;numerous computational systems;natural language input;minimal input data;conventional cognitive models;working memory;short-term memory;long-term memory;natural language command;feedback system},
}

{"_id":"HY4denCAkJDHFTdBW","bibbaseid":"saini-sahula-cognitivearchitecturefornaturallanguagecomprehension-2020","author_short":["Saini, S.","Sahula, V."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["S."],"propositions":[],"lastnames":["Saini"],"suffixes":[]},{"firstnames":["V."],"propositions":[],"lastnames":["Sahula"],"suffixes":[]}],"doi":"10.1049/ccs.2019.0017","journal":"IET Cognitive Computation and Systems","number":"1","title":"Cognitive architecture for natural language comprehension","url":"https://ieeexplore.ieee.org/document/9037560","volume":"2","year":"2020","issn":"2517-7567","pages":"23-31","abstract":"Human interactions with computers in natural language have always been a challenging task. Numerous computational systems are being designed to bring this interaction as close to the natural language commands as possible. Cognitive architectures are worthy solutions to solve this problem. In the present work, the authors have developed a cognitive architecture, which is capable of learning using natural language input. It can learn with minimal input data and has been designed using neural networks. The system is inspired by conventional cognitive models for working memory. They have proposed the system with a central executive unit controlling the short-term memory and long-term memory to comprehend the text input given as a natural language command and generate the output in natural language. The system comprises a feedback system as well to improve the learning process. The model has been trained using 1000 English sentences taught to primary school students. The system is capable of comprehending the relations between words, verbs, nouns, pronouns, adjectives, and generates logical reasoning-based answers.","file":":https\\://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9037560:","keywords":"neural nets;natural language processing;computer aided instruction;natural languages;cognition;learning (artificial intelligence);cognitive systems;inference mechanisms;cognitive architecture;natural language comprehension;human interactions;numerous computational systems;natural language input;minimal input data;conventional cognitive models;working memory;short-term memory;long-term memory;natural language command;feedback system","bibtex":"@Article{saini2020ccs,\r\n author = {S. {Saini} and V. {Sahula}},\r\n doi = {10.1049/ccs.2019.0017},\r\n journal = {IET Cognitive Computation and Systems},\r\n number = {1},\r\n title = {Cognitive architecture for natural language comprehension},\r\n url = {https://ieeexplore.ieee.org/document/9037560},\r\n volume = {2},\r\n year = {2020},\r\n issn = {2517-7567},\r\n pages = {23-31},\r\n abstract = {Human interactions with computers in natural language have always been a challenging task. Numerous computational systems are being designed to bring this interaction as close to the natural language commands as possible. Cognitive architectures are worthy solutions to solve this problem. In the present work, the authors have developed a cognitive architecture, which is capable of learning using natural language input. It can learn with minimal input data and has been designed using neural networks. The system is inspired by conventional cognitive models for working memory. They have proposed the system with a central executive unit controlling the short-term memory and long-term memory to comprehend the text input given as a natural language command and generate the output in natural language. The system comprises a feedback system as well to improve the learning process. The model has been trained using 1000 English sentences taught to primary school students. The system is capable of comprehending the relations between words, verbs, nouns, pronouns, adjectives, and generates logical reasoning-based answers.},\r\n file = {:https\\://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9037560:},\r\n keywords = {neural nets;natural language processing;computer aided instruction;natural languages;cognition;learning (artificial intelligence);cognitive systems;inference mechanisms;cognitive architecture;natural language comprehension;human interactions;numerous computational systems;natural language input;minimal input data;conventional cognitive models;working memory;short-term memory;long-term memory;natural language command;feedback system},\r\n}\r\n\r\n","author_short":["Saini, S.","Sahula, V."],"key":"saini2020ccs","id":"saini2020ccs","bibbaseid":"saini-sahula-cognitivearchitecturefornaturallanguagecomprehension-2020","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/9037560"},"keyword":["neural nets;natural language processing;computer aided instruction;natural languages;cognition;learning (artificial intelligence);cognitive systems;inference mechanisms;cognitive architecture;natural language comprehension;human interactions;numerous computational systems;natural language input;minimal input data;conventional cognitive models;working memory;short-term memory;long-term memory;natural language command;feedback system"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/sM7jHreBJqBTJiuKp","dataSources":["pSNhXMFJxYm9uTCNt","PTLrA9fS3hyN8EQmt","t6wpuLQ6zczqJP6ot"],"keywords":["neural nets;natural language processing;computer aided instruction;natural languages;cognition;learning (artificial intelligence);cognitive systems;inference mechanisms;cognitive architecture;natural language comprehension;human interactions;numerous computational systems;natural language input;minimal input data;conventional cognitive models;working memory;short-term memory;long-term memory;natural language command;feedback system"],"search_terms":["cognitive","architecture","natural","language","comprehension","saini","sahula"],"title":"Cognitive architecture for natural language comprehension","year":2020}