Research Trends for Named Entity Recognition in Hindi Language

Jain, Arti; Tayal, Devendra K.; Yadav, Divakar; Arora, Anuja

doi:10.1007/978-3-030-25797-2_10

Cited by 9 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first phase-pre-processing accompanies various operations (Section 4.1) -input restriction, sentence tokenization, removal of punctuation, word tokenization, stop-word elimination, word stemming and normalization. Resultant cleaned Punjabi text undergoes the processing phase (Section 4.2) where several features such as headline, title summary, sentence length, TF-ISF, NER (Jain et al, 2020), cue phrase, and English-Punjabi common nouns are applied and sentence scores are calculated. Weight is assigned to each feature, and sentence informative score is calculated to generate fitness function for the particle swarm optimization algorithm.…”

Section: Proposed Framework For Summarization Of Punjabi Textmentioning

confidence: 99%

Particle Swarm Optimization for Punjabi Text Summarization

Jain

Yadav

Arora

2021

International Journal of Operations Research and Information Systems

Self Cite

View full text Add to dashboard Cite

Particle swarm optimization (PSO) algorithm is proposed to deal with text summarization for the Punjabi language. PSO is based on intelligence that predicts among a given set of solutions which is the best solution. The search is carried out by extremely high-speed particles. It updates particle position and velocity at the end of iteration so that during the development of generations, the personal best solution and global best solution are updated. Calculation within PSO is performed using fitness function which looks into various statistical and linguistic features of the Punjabi datasets. Two Punjabi datasets—monolingual Punjabi corpus from Indian Languages Corpora Initiative Phase-II and Punjabi-Hindi parallel corpus—are considered. The parallel corpus comprises 1,000 Punjabi sentences from the tourism domain while monolingual corpus contains 30,000 Punjabi sentences of the general domain. ROUGE measures evaluate summary where the highest measure, ROUGE-1, is achieved for parallel corpus with precision, recall, and F-measure as 0.7836, 0.7957, and 0.7896, respectively.

show abstract

Section: Proposed Framework For Summarization Of Punjabi Textmentioning

confidence: 99%

Particle Swarm Optimization for Punjabi Text Summarization

Jain

Yadav

Arora

2021

International Journal of Operations Research and Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this study, the pre-processing phase includes sentence segmentation, word tokenization, stemming, Part-of-Speech (POS) tagging, and stop-words removal. The feature extraction phase includes eight features: sentence paragraph position, numerical data, sentence length, keywords within a sentence, sentence similarity, Named Entities (NEs) [11,12], English-Hindi words within a sentence, and Term Frequency (TF)-Inverse Sentence Frequency (ISF). These features influence the importance of sentences using the weighted-learning concept so that final sentence scores are calculated using feature weights.…”

Section: Introductionmentioning

confidence: 99%

“…The proportion of individual fitness to total fitness of the entire population decides-the area of the sector for the individual and the probability of the individual being selected for the next generation. So, at first, it calculates the sum of fitness values of all the chromosomes, i.e., cumulative fitness of the entire population, and then calculates the probability of each chromosome using Equation (11).…”

mentioning

confidence: 99%

Automatic Text Summarization for Hindi Using Real Coded Genetic Algorithm

et al. 2022

Self Cite

View full text Add to dashboard Cite

In the present scenario, Automatic Text Summarization (ATS) is in great demand to address the ever-growing volume of text data available online to discover relevant information faster. In this research, the ATS methodology is proposed for the Hindi language using Real Coded Genetic Algorithm (RCGA) over the health corpus, available in the Kaggle dataset. The methodology comprises five phases: preprocessing, feature extraction, processing, sentence ranking, and summary generation. Rigorous experimentation on varied feature sets is performed where distinguishing features, namely- sentence similarity and named entity features are combined with others for computing the evaluation metrics. The top 14 feature combinations are evaluated through Recall-Oriented Understudy for Gisting Evaluation (ROUGE) measure. RCGA computes appropriate feature weights through strings of features, chromosomes selection, and reproduction operators: Simulating Binary Crossover and Polynomial Mutation. To extract the highest scored sentences as the corpus summary, different compression rates are tested. In comparison with existing summarization tools, the ATS extractive method gives a summary reduction of 65%.

show abstract

Addressing cold start in recommender systems with neural networks: a literature survey

Berisha

Bytyçi

2023

International Journal of Computers and Applications

View full text Add to dashboard Cite

Research Trends for Named Entity Recognition in Hindi Language

Cited by 9 publications

References 41 publications

Particle Swarm Optimization for Punjabi Text Summarization

Particle Swarm Optimization for Punjabi Text Summarization

Automatic Text Summarization for Hindi Using Real Coded Genetic Algorithm

Addressing cold start in recommender systems with neural networks: a literature survey

Contact Info

Product

Resources

About