(refs) Tag: Visual edit |
(add link) Tag: Visual edit |
||
| (One intermediate revision by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | SQuAD is a line of question-answering datasets created by Stanford. The first incarnation is published in Rajpurkar et al. (2016)<ref>Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. In ''EMNLP 2016'' (pp. 2383–2392). http://doi.org/10.18653/v1/D16-1264</ref> and quickly became popular. However, results on this dataset quickly surpass human performance with the application of what Percy Liang has [https://newgeneralization.github.io/slides/PercyLiang.pdf called] "cheap tricks". Adversarial SQuAD (Jia and Liang, 2017<ref>Jia, R., & Liang, P. (2017). Adversarial Examples for Evaluating Reading Comprehension Systems. ''EMNLP 2017'', 2021–2031. Retrieved from http://arxiv.org/abs/1707.07328</ref>) and SQuAD 2.0 (Rajpurkar et al. 2018<ref>Rajpurkar, P., Jia, R., & Liang, P. (2018). Know What You Don’t Know: Unanswerable Questions for SQuAD. In ''Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)'' (pp. 784–789). Association for Computational Linguistics.</ref>) are created to evaluate for higher inference skills. |
+ | [https://rajpurkar.github.io/SQuAD-explorer/ SQuAD] is a line of question-answering datasets created by Stanford. The first incarnation is published in Rajpurkar et al. (2016)<ref>Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. In ''EMNLP 2016'' (pp. 2383–2392). http://doi.org/10.18653/v1/D16-1264</ref> and quickly became popular. However, results on this dataset quickly surpass human performance with the application of what Percy Liang has [https://newgeneralization.github.io/slides/PercyLiang.pdf called] "cheap tricks". Adversarial SQuAD (Jia and Liang, 2017<ref>Jia, R., & Liang, P. (2017). Adversarial Examples for Evaluating Reading Comprehension Systems. ''EMNLP 2017'', 2021–2031. Retrieved from http://arxiv.org/abs/1707.07328</ref>) and SQuAD 2.0 (Rajpurkar et al. 2018<ref>Rajpurkar, P., Jia, R., & Liang, P. (2018). Know What You Don’t Know: Unanswerable Questions for SQuAD. In ''Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)'' (pp. 784–789). Association for Computational Linguistics.</ref>) are created to evaluate for higher inference skills. |
| + | |||
| + | == Open-source software packages == |
||
| + | * [https://allennlp.org/models AllenNLP] |
||
| + | * [https://github.com/jojonki/BiDAF BiDAF] |
||
== References == |
== References == |
||
Latest revision as of 09:44, 11 August 2018
SQuAD is a line of question-answering datasets created by Stanford. The first incarnation is published in Rajpurkar et al. (2016)[1] and quickly became popular. However, results on this dataset quickly surpass human performance with the application of what Percy Liang has called "cheap tricks". Adversarial SQuAD (Jia and Liang, 2017[2]) and SQuAD 2.0 (Rajpurkar et al. 2018[3]) are created to evaluate for higher inference skills.
Open-source software packages[]
References[]
- ↑ Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. In EMNLP 2016 (pp. 2383–2392). http://doi.org/10.18653/v1/D16-1264
- ↑ Jia, R., & Liang, P. (2017). Adversarial Examples for Evaluating Reading Comprehension Systems. EMNLP 2017, 2021–2031. Retrieved from http://arxiv.org/abs/1707.07328
- ↑ Rajpurkar, P., Jia, R., & Liang, P. (2018). Know What You Don’t Know: Unanswerable Questions for SQuAD. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (pp. 784–789). Association for Computational Linguistics.