Home > Research > Publications & Outputs > A Sense Annotated Corpus for All-Words Urdu Wor...

Links

Text available via DOI:

View graph of relations

A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation. / Saeed, Ali; Nawab, Rao Muhammad Adeel ; Stevenson, Mark et al.
In: ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Vol. 18, No. 4, 40, 01.05.2019.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Saeed, A, Nawab, RMA, Stevenson, M & Rayson, PE 2019, 'A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation', ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), vol. 18, no. 4, 40. https://doi.org/10.1145/3314940

APA

Saeed, A., Nawab, R. M. A., Stevenson, M., & Rayson, P. E. (2019). A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 18(4), Article 40. https://doi.org/10.1145/3314940

Vancouver

Saeed A, Nawab RMA, Stevenson M, Rayson PE. A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP). 2019 May 1;18(4):40. doi: 10.1145/3314940

Author

Saeed, Ali ; Nawab, Rao Muhammad Adeel ; Stevenson, Mark et al. / A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation. In: ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP). 2019 ; Vol. 18, No. 4.

Bibtex

@article{81e4ced7d8f74686abab9873423be93e,
title = "A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation",
abstract = "Word Sense Disambiguation (WSD) aims to automatically predict the correct sense of a word used in a given context. All human languages exhibit word sense ambiguity, and resolving this ambiguity can be difficult. Standard benchmark resources are required to develop, compare, and evaluate WSD techniques. These are available for many languages, but not for Urdu, despite this being a language with more than 300 million speakers and large volumes of text available digitally. To fill this gap, this study proposes a novel benchmark corpus for the Urdu All-Words WSD task. The corpus contains 5,042 words of Urdu running text in which all ambiguous words (856 instances) are manually tagged with senses from the Urdu Lughat dictionary. A range of baseline WSD models based on n-gram are applied to the corpus, and the best performance (accuracy of 57.71%) is achieved using word 4-gram. The corpus is freely available to the research community to encourage further WSD research in Urdu.",
author = "Ali Saeed and Nawab, {Rao Muhammad Adeel} and Mark Stevenson and Rayson, {Paul Edward}",
year = "2019",
month = may,
day = "1",
doi = "10.1145/3314940",
language = "English",
volume = "18",
journal = "ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)",
issn = "2375-4699",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

RIS

TY - JOUR

T1 - A Sense Annotated Corpus for All-Words Urdu Word Sense Disambiguation

AU - Saeed, Ali

AU - Nawab, Rao Muhammad Adeel

AU - Stevenson, Mark

AU - Rayson, Paul Edward

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Word Sense Disambiguation (WSD) aims to automatically predict the correct sense of a word used in a given context. All human languages exhibit word sense ambiguity, and resolving this ambiguity can be difficult. Standard benchmark resources are required to develop, compare, and evaluate WSD techniques. These are available for many languages, but not for Urdu, despite this being a language with more than 300 million speakers and large volumes of text available digitally. To fill this gap, this study proposes a novel benchmark corpus for the Urdu All-Words WSD task. The corpus contains 5,042 words of Urdu running text in which all ambiguous words (856 instances) are manually tagged with senses from the Urdu Lughat dictionary. A range of baseline WSD models based on n-gram are applied to the corpus, and the best performance (accuracy of 57.71%) is achieved using word 4-gram. The corpus is freely available to the research community to encourage further WSD research in Urdu.

AB - Word Sense Disambiguation (WSD) aims to automatically predict the correct sense of a word used in a given context. All human languages exhibit word sense ambiguity, and resolving this ambiguity can be difficult. Standard benchmark resources are required to develop, compare, and evaluate WSD techniques. These are available for many languages, but not for Urdu, despite this being a language with more than 300 million speakers and large volumes of text available digitally. To fill this gap, this study proposes a novel benchmark corpus for the Urdu All-Words WSD task. The corpus contains 5,042 words of Urdu running text in which all ambiguous words (856 instances) are manually tagged with senses from the Urdu Lughat dictionary. A range of baseline WSD models based on n-gram are applied to the corpus, and the best performance (accuracy of 57.71%) is achieved using word 4-gram. The corpus is freely available to the research community to encourage further WSD research in Urdu.

U2 - 10.1145/3314940

DO - 10.1145/3314940

M3 - Journal article

VL - 18

JO - ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)

JF - ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)

SN - 2375-4699

IS - 4

M1 - 40

ER -