A bootstrapping method for development of Treebank

Zarei, Farzaneh; Basirat, Ali; Faili, Heshaam; Mirain, M.

doi:10.1080/0952813x.2015.1057239

Cited by 2 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this approach, a pretrained tagger is used to tag the words of the sentences which may then be manually corrected and included in the gold standard training corpus. The tagger is then retrained using this corpus to label next batch of sentences and this process of retraining and correction continues iteratively until some termination criteria is met [17]. Since this work builds upon the work of [3], same 500 preprocessed tweets (13,643 tokens) used in [3] were selected for performing bootstrapping experiments.…”

Section: Methodsmentioning

confidence: 99%

Performance Comparison of Bootstrapped Statistical Taggers on Urdu Tweets

Baig¹,

Rahman²,

Abrejo³

et al. 2021

IJSRP

View full text Add to dashboard Cite

Twitter, a social media platform has experienced substantial growth over the last few years. Thus, huge number of tweets from various communities is available and used for various NLP applications such as Opinion mining, information extraction, sentiment analysis etc. One of the key pre-processing steps in such NLP applications is Part-of-Speech (POS) tagging. POS tagging of Twitter data (also called noisy text) is different than conventional POS tagging due to informal nature and presence of Twitter specific elements. Resources for POS tagging of tweet specific data are mostly available for English. Though, availability of tagset and language independent statistical taggers do provide opportunity for resource-poor languages such as Urdu to expand coverage of NLP tools to this new domain of POS tagging for which little effort has been reported. The aim of this study is twofold. First, is to investigate how well the statistical taggers developed for POS tagging of structured text fare in the domain of tweet POS tagging. Secondly, how can these taggers be used to overcome the bottleneck of manually annotated corpus for this new domain. To this end, Stanford and MorphoDiTa taggers were trained on 500 Urdu tweet gold-standard corpus and were utilized for semi-automatic corpus annotation in bootstrapped fashion. Five bootstrapping iterations for both the taggers were performed. At the end of each iteration, the performance of taggers was evaluated against the development set and automatically tagged, manually corrected 100 tweets were added in the training set to retrain both models. Finally, at the end of last iteration, tagger performance was evaluated against test set. Stanford tagger achieved an accuracy of 93.8% Precision, 92.9% Recall and 93.3% F-Measure. Whereas, MorphoDiTa tagger achieved an accuracy of 93.5% Precision, 92.6% Recall and 93% F-Measure. A thorough error analysis on the output of both taggers is also presented.

show abstract

Section: Methodsmentioning

confidence: 99%

Performance Comparison of Bootstrapped Statistical Taggers on Urdu Tweets

Baig¹,

Rahman²,

Abrejo³

et al. 2021

IJSRP

View full text Add to dashboard Cite

show abstract

“…To induce classifiers from training data, MaltParser uses two different built-in learning libraries: liblinear and libsvm. Liblinear library supports linear classification [24], and libsvm is for Support Vector Machines [23].…”

Section: Parsermentioning

confidence: 99%

“…Researchers need reliable strategies for speeding up the annotation process without biassing the gold standard [8]. Bootstrapping is a novel approach that attempts to iteratively generating treebanks in an efficient and cost-effective manner [23]. During bootstrapping process, a trained parser is used to pre-parse raw text, which is then manually corrected by human annotators [9].…”

Section: Introductionmentioning

confidence: 99%

Bootstrapping Dependency Treebank of Urdu Noisy Text

2021

IJETER

View full text Add to dashboard Cite

This paper describes how bootstrapping was used to extend the development of the Urdu Noisy Text dependency treebank. To overcome the bottleneck of manually annotating corpus for a new domain of user-generated text, MaltParser, an opensource, data-driven dependency parser, is used to bootstrap the treebank in semi-automatic manner for corpus annotation after being trained on 500 tweet Urdu Noisy Text Dependency Treebank. Total four bootstrapping iterations were performed. At the end of each iteration, 300 Urdu tweets were automatically tagged, and the performance of parser model was evaluated against the development set. 75 automatically tagged tweets were randomly selected out of pre-tagged 300 tweets for manual correction, which were then added in the training set for parser retraining. Finally, at the end of last iteration, parser performance was evaluated against test set. The final supervised bootstrapping model obtains a LA of 72.1%, UAS of 75.7% and LAS of 64.9%, which is a significant improvement over baseline score of 69.8% LA, 74% UAS, and 62.9% LAS

show abstract

A bootstrapping method for development of Treebank

Cited by 2 publications

References 11 publications

Performance Comparison of Bootstrapped Statistical Taggers on Urdu Tweets

Performance Comparison of Bootstrapped Statistical Taggers on Urdu Tweets

Bootstrapping Dependency Treebank of Urdu Noisy Text

Contact Info

Product

Resources

About