%0 Generic %1 sharma2019natural %A Sharma, Lakshay %A Graesser, Laura %A Nangia, Nikita %A Evci, Utku %D 2019 %K dl nlp %T Natural Language Understanding with the Quora Question Pairs Dataset %U http://arxiv.org/abs/1907.01041 %X This paper explores the task Natural Language Understanding (NLU) by looking at duplicate question detection in the Quora dataset. We conducted extensive exploration of the dataset and used various machine learning models, including linear and tree-based models. Our final finding was that a simple Continuous Bag of Words neural network model had the best performance, outdoing more complicated recurrent and attention based models. We also conducted error analysis and found some subjectivity in the labeling of the dataset.

@misc{sharma2019natural, abstract = {This paper explores the task Natural Language Understanding (NLU) by looking at duplicate question detection in the Quora dataset. We conducted extensive exploration of the dataset and used various machine learning models, including linear and tree-based models. Our final finding was that a simple Continuous Bag of Words neural network model had the best performance, outdoing more complicated recurrent and attention based models. We also conducted error analysis and found some subjectivity in the labeling of the dataset.}, added-at = {2020-02-24T23:57:30.000+0100}, author = {Sharma, Lakshay and Graesser, Laura and Nangia, Nikita and Evci, Utku}, biburl = {https://www.bibsonomy.org/bibtex/2aa8cb8cf795b3b412281eb8ec8a7e9c1/bechr7}, description = {[1907.01041] Natural Language Understanding with the Quora Question Pairs Dataset}, interhash = {5b580bab913f94210155250e68500fcf}, intrahash = {aa8cb8cf795b3b412281eb8ec8a7e9c1}, keywords = {dl nlp}, note = {cite arxiv:1907.01041}, timestamp = {2020-02-24T23:57:30.000+0100}, title = {Natural Language Understanding with the Quora Question Pairs Dataset}, url = {http://arxiv.org/abs/1907.01041}, year = 2019 }