An Artificial Language Evaluation of Distributional Semantic Models

Fatemeh Torabi Asr, Michael Jones
2017 Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)  
Recent studies of distributional semantic models have set up a competition between word embeddings obtained from predictive neural networks and word vectors obtained from count-based models. This paper is an attempt to reveal the underlying contribution of additional training data and post-processing steps on each type of model in word similarity and relatedness inference tasks. We do so by designing an artificial language, training a predictive and a count-based model on data sampled from this
more » ... a sampled from this grammar, and evaluating the resulting word vectors in paradigmatic and syntagmatic tasks defined with respect to the grammar.
doi:10.18653/v1/k17-1015 dblp:conf/conll/AsrJ17 fatcat:xctz3m4qk5gbhgu2ehog7guk4a