Hybrid Approach for Named Entity Recognition

Abstract

This paper proposes the Named Entity Recognition (NER) system for Punjabi language using a hybrid approach in which rule based approach and machine learning approach i.e. Hidden Markov Model (HMM) is combined. With no Dataset available, the Named Entities (NEs) were manually tagged which led us to the creation of training and testing dataset, under the linguistic supervision. Using hybrid approach, the proposed system is able to recognize Name of person

Limitations of information extraction methods and techniques for heterogeneous unstructured big data

“…22 Combination of HMM (Hidden Markov Model) with hand rules for the Punjabi language has shown pretty notable results as compared to a supervised machine learning method that achieved the precision of 72.92% and 47.57% by using HMM only. 23 A semi-hybrid approach by combining HMM and some rule-based approaches for PoS tagging and entity detection from the Nepali language has been proposed to extract named entity-specific classes that include the name of the person, location, number, organization, currency, and quantifier. 24 Combination of dictionary-based, rule-based, and machine learning has been used to extract molecules and related properties from the scientific literature in biomedical domain.…”

Representing and Reasoning with Context-Sensitive Vague Place Descriptions

“…The hybrid methods employed in various research are discussed in Table 3. Sequential labeler based on the linear Conditional Random Fields for clustering similar tweets [247] Conditional Random Field to identify named-entities from homeopathy diagnosis discussion forum [253] a novel kernel function for support vector machines for sequential labeling tasks like named entity recognition [314] Convolutional Neural Network (CNN) extraction of location from tweet text [218] Table 3: Overview of different Hybrid NER approaches used for extracting information related to entities NER Hybrid Approaches Purpose Reference maximum entropy model language-specific rules gazetteers for the Hindi and Bengali language text [313] rule-based pattern extractor using link grammar parser Stanford PoS tagger semi-supervised classifier for entity labeling [318] Conditional Random Fields (CRF) with dictionary a chemical NER system [309] Support Vector Machine Conditional Random Fields for biological entities [417] Supervised tagger TnT rule-based support vector machine (SVM) health and tourism text documents in Malayalam language [182] Combination of Hidden Markov Model with manually crafted rules for the Punjabi language [32] Hidden Markov Model plus rules (PoS tagging for entity detection) to extract named entity-specific classes from the Nepali language [335] Combination of dictionary-based, rule-based, machine learning to extract molecules related properties from scientific literature in biomedical domain [106] Combined dictionary-based approach fuzzy matching stemmed matching generates a set of annotation from the clinical text [296] Support Vector Machine Hidden Markov Model linguistic pre-processing methods to identify gene and protein from text without using external knowledge base [25] manual engineered rule-based predecessor lexical resources and pattern for semantic indexing of the Turkish text [212] Combination of Hidden Markov Model with a gazetteer for tourism text in Hindi [177] using morphological rules to extract nouns from classical documents in the Malay language [319] Rule-based Conditional Random Fields Random Forest Bidirectional-LSTM approach Named Entity Recognition for sensitive data in Portuguese language [97] Tables 1,2,3 survey how information retrieval for extracting and recognizing entities in a variety of disciplines, from geography to biology, is being pursued. Nevertheless, as can be observed, the primary focus is on lan-guage comprehension and identifying diverse sets of entities from other languages.…”