%0 Conference Paper %1 snow2008cheap %A Snow, Rion %A O'Connor, Brendan %A Jurafsky, Daniel %A Ng, Andrew %B Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing %C Honolulu, Hawaii %D 2008 %I Association for Computational Linguistics %K annotation computing crowdsourcing crowdworker evaluation expert human language natural nlp processing social %P 254--263 %T Cheap and Fast -- But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks %U https://www.aclweb.org/anthology/D08-1027 %X Human linguistic annotation is crucial for many natural language processing tasks but can be expensive and time-consuming. We explore the use of Amazon's Mechanical Turk system, a significantly cheaper and faster method for collecting annotations from a broad base of paid non-expert contributors over the Web. We investigate five tasks: affect recognition, word similarity, recognizing textual entailment, event temporal ordering, and word sense disambiguation. For all five, we show high agreement between Mechanical Turk non-expert annotations and existing gold standard labels provided by expert labelers. For the task of affect recognition, we also show that using non-expert labels for training machine learning algorithms can be as effective as using gold standard annotations from experts. We propose a technique for bias correction that significantly improves annotation quality on two tasks. We conclude that many large labeling tasks can be effectively designed and carried out in this method at a fraction of the usual expense.

@inproceedings{snow2008cheap, abstract = {Human linguistic annotation is crucial for many natural language processing tasks but can be expensive and time-consuming. We explore the use of Amazon's Mechanical Turk system, a significantly cheaper and faster method for collecting annotations from a broad base of paid non-expert contributors over the Web. We investigate five tasks: affect recognition, word similarity, recognizing textual entailment, event temporal ordering, and word sense disambiguation. For all five, we show high agreement between Mechanical Turk non-expert annotations and existing gold standard labels provided by expert labelers. For the task of affect recognition, we also show that using non-expert labels for training machine learning algorithms can be as effective as using gold standard annotations from experts. We propose a technique for bias correction that significantly improves annotation quality on two tasks. We conclude that many large labeling tasks can be effectively designed and carried out in this method at a fraction of the usual expense.}, added-at = {2020-10-21T12:48:47.000+0200}, address = {Honolulu, Hawaii}, author = {Snow, Rion and O'Connor, Brendan and Jurafsky, Daniel and Ng, Andrew}, biburl = {https://www.bibsonomy.org/bibtex/2287dc13d201058313d7a17e462b6af7e/jaeschke}, booktitle = {Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing}, description = {Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks - ACL Anthology}, interhash = {fa24c8db32accb61e8bf025b23574986}, intrahash = {287dc13d201058313d7a17e462b6af7e}, keywords = {annotation computing crowdsourcing crowdworker evaluation expert human language natural nlp processing social}, month = oct, pages = {254--263}, publisher = {Association for Computational Linguistics}, timestamp = {2020-10-21T12:48:47.000+0200}, title = {Cheap and Fast -- But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks}, url = {https://www.aclweb.org/anthology/D08-1027}, year = 2008 }