Evaluation of Unsupervised Compositional Representations
arXiv:1806.04713
Abstract
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.
12 pages, 5 figures. COLING 2018
References in corpus (5)
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
- A simple but tough-to-beat baseline for the Fake News Challenge stance detection task
- Evaluating Neural Word Representations in Tensor-Based Compositional Settings