Information Extraction for Conversational Systems in Indian Languages - Arnekt IECSIL

Hb, Barathi Ganesh; Reshma, U; Kale, Mandar; Mankame, Prachi; Kulkarni, Gouri; Kale, Anitha; M, Anand Kumar

doi:10.1145/3293339.3293344

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ARNEKT IECSIL FIRE 2018 NER Dataset This corpus was compiled from the abstracts and info-box properties from DBpedia for the (IECSIL) shared task (Hullathy Balakrishnan et al, 2018) CUSAT NER Dataset This is a manually annotated NER data set developed by CUSAT. 6 It is based on the CUSAT POS tagged data set for Malayalam (Ajees and Idicula, 2018).…”

Section: Data Sets and Resourcesmentioning

confidence: 99%

EmployingWikipedia as a Resource for Named Entity Recognition in Morphologically Complex Under-Resourced Languages

Krishnan¹,

Ziehe²,

Pannach³

et al. 2021

Proceedings of the 14thWorkshop on Building and Using Comparable Corpora (BUCC 2021)

View full text Add to dashboard Cite

We propose a novel approach for rapid prototyping of named entity recognisers through the development of semi-automatically annotated data sets. We demonstrate the proposed pipeline on two under-resourced agglutinating languages: the Dravidian language Malayalam and the Bantu language isiZulu. Our approach is weakly supervised and bootstraps training data from Wikipedia and Google Knowledge Graph. Moreover, our approach is relatively language independent and can consequently be ported quickly (and hence cost-effectively) from one language to another, requiring only minor language-specific tailoring.

show abstract

Section: Data Sets and Resourcesmentioning

confidence: 99%

EmployingWikipedia as a Resource for Named Entity Recognition in Morphologically Complex Under-Resourced Languages

Krishnan¹,

Ziehe²,

Pannach³

et al. 2021

Proceedings of the 14thWorkshop on Building and Using Comparable Corpora (BUCC 2021)

View full text Add to dashboard Cite

show abstract

A Relation Extraction System for Indian Languages

Pareed¹,

Idicula²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Relation Extraction is an important subtask of Information Extraction that involves extracting significant facts from natural language text. Extracting structured information from the plaintext is the ultimate goal of IE systems. The Indian language content on the internet is increasing day to day. Extracting relevant information from this huge unstructured data is a challenging task especially when the business firms are interested in ascertaining public view on their products and processes. The primary objective of relation extraction systems is to find those entities which can be targeted through social networking and digital marketing. Cannibalisation of the product is nowadays done using these Social Networks. Different methods are proposed and experimented for Relation extraction problems. In this paper, we propose a Relation Extraction system using Convolutional Neural Networks. Deep learning based methods have produced state of the art results in many domains. Training and testing are conducted using the shared corpus provided by 'ARNEKT-IECSIL 2018' competition organisers. The evaluation results show that the proposed system could outperform most of the reported methods in the competition.

show abstract

Information Extraction for Conversational Systems in Indian Languages - Arnekt IECSIL

Cited by 2 publications

References 1 publication

EmployingWikipedia as a Resource for Named Entity Recognition in Morphologically Complex Under-Resourced Languages

EmployingWikipedia as a Resource for Named Entity Recognition in Morphologically Complex Under-Resourced Languages

A Relation Extraction System for Indian Languages

Contact Info

Product

Resources

About