Natural Language Understanding with the Quora Question Pairs Dataset

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.

References in corpus (4)

• Scikit-learn: Machine Learning in Python
• Sequence to Sequence Learning with Neural Networks
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• TnT - A Statistical Part-of-Speech Tagger

Cited by in corpus (9)

• On Transferability of Prompt Tuning for Natural Language Processing
• InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
• Parallelizing Legendre Memory Unit Training
• ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning
• PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
• Exploring the Impact of Model Scaling on Parameter-Efficient Tuning
• Retrieve Synonymous keywords for Frequent Queries in Sponsored Search in a Data Augmentation Way
• Retraining DistilBERT for a Voice Shopping Assistant by Using Universal Dependencies
• Learning Similarity between Movie Characters and Its Potential Implications on Understanding Human Experiences