Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao, Lawrence Carin

Many deep learning architectures have been proposed to model the \emph{compositionality} in text sequences, requiring substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the added value of sophisticated compositional functions. In this paper, we conduct a point-by-point comparative study between Simple Word-Embedding-based Models (SWEMs), consisting of parameter-free pooling operations, relative to word-embedding-based RNN/CNN models. Surprisingly, SWEMs exhibit comparable or even superior performance in the majority of cases considered. Based upon this understanding, we propose two additional pooling strategies over learned word embeddings: ($i$) a max-pooling operation for improved interpretability; and ($ii$) a hierarchical pooling operation, which preserves spatial ($n$-gram) information within text sequences. We present experiments on 17 datasets encompassing three tasks: ($i$) (long) document classification; ($ii$) text sequence matching; and ($iii$) short text tasks, including classification and tagging.