Evaluation of unsupervised compositional representations

Hanan Aldarmaki, The George Washington University & Mohamed bin Zayed University of Artificial Intelligence
Mona Diab, The George Washington University


We evaluated various compositional models, from bag-of-words representations to compositional RNN-based models, on several extrinsic supervised and unsupervised evaluation benchmarks. Our results confirm that weighted vector averaging can outperform context-sensitive models in most benchmarks, but structural features encoded in RNN models can also be useful in certain classification tasks. We analyzed some of the evaluation datasets to identify the aspects of meaning they measure and the characteristics of the various models that explain their performance variance. © 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.