Morphologically rich Urdu grammar parsing using Earley algorithm

Abbas, Qaiser

doi:10.1017/s1351324915000133

Cited by 12 publications

(15 citation statements)

References 27 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for as, the phrase structure is concerned the URDU.KON-TB treebank has been evaluated and results are reported in [16]. To use the URDU.KON-TB treebank, we have converted the annotated data according to the format of the MaltParser's input e.g.…”

Section: Resultsmentioning

confidence: 99%

“…They desired to add chunk heads to check intra-chunk dependencies. Some other experiments had also been performed in many studies like [4], [5], [6], [8], [10], [11], [12], [13], [15], [16], [17], [20], [21] for various languages and results are reported in favor of the MaltParser.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

“…After this evaluation check their usefulness is normally reported. As for as, the phrase structure is concerned the URDU.KON-TB treebank has been evaluated and results are reported in [16]. However, this treebank has not been evaluated in the dependency parsing domain.…”

Section: Problem Statementmentioning

confidence: 99%

“…As we are going to develop and experiment the computational resources in the domain of dependency parsing, so our research objectives/tasks will include the following 1. We will measure the compatibility of the URDU.KON-TB treebank w.r.t the format of the MaltParseras the treebank has the HDS annotation scheme encoded in it [16] and then we will claim its usability.…”

Section: Problem Statementmentioning

confidence: 99%

“…Here is graphic representation of the given sentence which showing Semi-Semantic POS (SSP), Semi-Semantic Syntactic (SSS) and Functional (F) tagset [16].…”

Section: Data Conversion Processmentioning

confidence: 99%

See 4 more Smart Citations

Dependency Parsing using the URDU.KON-TB Treebank

Munir¹,

Abbas²,

Jamil³

2017

IJCA

View full text Add to dashboard Cite

In this paper, we present evaluation of URDU.KON-TB in the dependency parsing domain. The URDU.KON-TB treebank is developed on the bases of the phrase structure and hyper dependency structure which are only functional constituent's label. Treebank was annotated with three levels of annotation tagset, the semi-semantic POS (SSP), semi-semantic Syntactic (SSS) and Functional (F) tagset and was checked for the Phrase Structure Parsing domain. To evaluate this treebank in the Dependency Parsing domain we have selected MaltParser. To use data in the parser, we have converted the URDU.KON-TB treebank annotated data according to the CONLL format. The compatibility of data to CoNLL is also measured along with usability of data in the dependency parsing domain. To make the data compatible, few assumptions are taken. The converted data is used to evaluate the system by dividing 80% data as training data and 20% data as testing data. We have performed eight experiments. Four experiments are conducted with six different feature models with converted data. The experiments results show URDU.KON-TB treebank is not suitable for the dependency parsing as dependency relation because Head information was missing in the treebank. We then performed four experiments with an assumption based enhancement by adding Head information. The algorithm used to train and test data is Nivre arc-agear algorithm. The new experiments show this treebank data can be used to develop new dependency treebank for Urdu. General Terms URDU.KON-TB, MaltParser and Dependency parsing

show abstract

Section: Resultsmentioning

confidence: 99%

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

“…Here is graphic representation of the given sentence which showing Semi-Semantic POS (SSP), Semi-Semantic Syntactic (SSS) and Functional (F) tagset [16].…”

Section: Data Conversion Processmentioning

confidence: 99%

See 3 more Smart Citations

Dependency Parsing using the URDU.KON-TB Treebank

Munir¹,

Abbas²,

Jamil³

2017

IJCA

View full text Add to dashboard Cite

show abstract

Next word prediction for Urdu language using deep learning models

Shahid,

Wali,

Bashir

2024

Computer Speech & Language

View full text Add to dashboard Cite

Urdu Named Entity Recognition System Using Deep Learning Approaches

Haq

Zhang

Khan

et al. 2022

The Computer Journal

View full text Add to dashboard Cite

Named entity recognition (NER) is a fundamental part of other natural language processing tasks such as information retrieval, question answering systems and machine translation. Progress and success have already been achieved in research on the English NER systems. However, the Urdu NER system is still in its infancy due to the complexity and morphological richness of the Urdu language. Existing Urdu NER systems are highly dependent on manual feature engineering and word embedding to capture similarity. Their performance lags if the words are previously unknown or infrequent. The feature-based models suffer from complicated feature engineering and are often highly reliant on external resources. To overcome these limitations in this study, we present several deep neural approaches that automatically learn features from the data and eliminate manual feature engineering. Our extension involved convolutional neural network to extract character-level features and combine them with word embedding to handle out-of-vocabulary words. The study also presents a tweets dataset in Urdu, annotated manually for five named entity classes. The effectiveness of the deep learning approaches is demonstrated on four benchmarks datasets. The proposed method demonstrates notable progress upon current state-of-the-art NER approaches in Urdu. The results show an improvement of 6.26% in the F1 score.

show abstract

Morphologically rich Urdu grammar parsing using Earley algorithm

Cited by 12 publications

References 27 publications

Dependency Parsing using the URDU.KON-TB Treebank

Dependency Parsing using the URDU.KON-TB Treebank

Next word prediction for Urdu language using deep learning models

Urdu Named Entity Recognition System Using Deep Learning Approaches

Contact Info

Product

Resources

About