On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis

Text preprocessing is often the first step in the pipeline of a Natural Language Processing (NLP) system, with potential impact in its final performance. Despite its importance, text preprocessing has not received much attention in the deep learning literature... In this paper we investigate the impact of simple text preprocessing decisions (particularly tokenizing, lemmatizing, lowercasing and multiword grouping) on the performance of a standard neural text classifier. We perform an extensive evaluation on standard benchmarks from text categorization and sentiment analysis. While our experiments show that a simple tokenization of input text is generally adequate, they also highlight significant degrees of variability across preprocessing techniques. This reveals the importance of paying attention to this usually-overlooked step in the pipeline, particularly when comparing different models. Finally, our evaluation provides insights into the best preprocessing practices for training word embeddings. read more

PDF Abstract WS 2018 PDF WS 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sentiment Analysis IMDb CNN+LSTM Accuracy 88.9 # 23
Text Classification Ohsumed CNN+Lowercased Accuracy 36.2 # 10
Sentiment Analysis SST-2 Binary classification CNN Accuracy 91.2 # 43

Methods


No methods listed for this paper. Add relevant methods here