An Improved Word Representation for Deep Learning Based NER in Indian Languages

Abstract

Named Entity Recognition (NER) is the process of identifying the elementary units in a text document and classifying them into predefined categories such as person, location, organization and so forth. NER plays an important role in many Natural Language Processing applications like information retrieval, question answering, machine translation and so forth. Resolving the ambiguities of lexical items involved in a text document is a challenging task. NER in Indian languages is always a complex task due to their morphological richness and agglutinative nature. Even though different solutions were proposed for NER, it is still an unsolved problem. Traditional approaches to Named Entity Recognition were based on the application of hand-crafted features to classical machine learning techniques such as Hidden Markov Model (HMM), Support Vector Machine (SVM), Conditional Random Field (CRF) and so forth. But the introduction of deep learning techniques to the NER problem changed the scenario, where the state of art results have been achieved using deep learning architectures. In this paper, we address the problem of effective word representation for NER in Indian languages by capturing the syntactic, semantic and morphological information. We propose a deep learning based entity extraction system for Indian languages using a novel combined word representation, including character-level, word-level and affix-level embeddings. We have used ‘ARNEKT-IECSIL 2018’ shared data for training and testing. Our results highlight the improvement that we obtained over the existing pre-trained word representations.

Systematic Literature Review on Named Entity Recognition: Approach, Method, and Application

“…English is the largest language dataset available for NER research because English is the most widely spoken language globally. NER research in other languages include Arabic [64,117,125,132,255], Chinese [51,52,105,156,159,180,256], German [269], Korean [115,130,196,258] and Indian [35,112,119,141]. Among the NER studies in Bahasa Indonesia have been conducted by Wintaka et [284].…”

State-of-art approach for Indian Language based on NER: Comprehensive Review

“…The authors trained supervised NER system using hierarchical neural networks and also used multilingual learning for NER in Indian languages. They empirically demonstrated the advantages over monolingual deep learning systems [76] and conventional machine learning systems with some feature engineering. With the use of multilingual learning, they were able to demonstrate that the improvement in low-resource language where NER performance is mostly attributable to multilingual learning acting as regularization, cross-lingual sub-word characteristics and a larger named entity vocabulary.…”

“…It is powerful approach that involves training neural networks on large datasets to perform tasks. In the context of NER, a deep learning (DL) [8], [76] approach uses neural networks to automatically identify and classify entities such as names of people, locations, organizations within a given data. In it, the input text converts into numerical representation that can be processed by neural networks.…”

“…Singh et al [82] proposed an annotated benchmark corpus for Gurmukhi script and also trained a model on the Spacy tool which contains 12k-sentences only using Punjabi corpus data. The remaining 3k-words were utilized to validate the results using the F1-score, which was picked as the evaluation metric using deep learning [76]. In this study, a unique method for extracting named entities from sentences written in the Gurmukhi script of the Punjabi language is proposed.…”

Editorial for the Special Issue on “Natural Language Processing and Text Mining”

“…The paper "An Improved Word Representation for Deep Learning Based NER in Indian Languages" [9] describes a named entity recognition system based on deep learning approaches for Indian languages. For this purpose, they use a novel combined word representation, including several levels of embeddings, namely character-level, word-level, and affix-level embeddings.…”