Michael Jones

Also published as: Michael P. Jones


pdf bib
Querying Word Embeddings for Similarity and Relatedness
Fatemeh Torabi Asr | Robert Zinkov | Michael Jones
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Word embeddings obtained from neural network models such as Word2Vec Skipgram have become popular representations of word meaning and have been evaluated on a variety of word similarity and relatedness norming data. Skipgram generates a set of word and context embeddings, the latter typically discarded after training. We demonstrate the usefulness of context embeddings in predicting asymmetric association between words from a recently published dataset of production norms (Jouravlev & McRae, 2016). Our findings suggest that humans respond with words closer to the cue within the context embedding space (rather than the word embedding space), when asked to generate thematically related words.


pdf bib
An Artificial Language Evaluation of Distributional Semantic Models
Fatemeh Torabi Asr | Michael Jones
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 abstractive 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 framework, training a predictive and a count-based model on data sampled from this grammar, and evaluating the resulting word vectors in paradigmatic and syntagmatic tasks defined with respect to the grammar.


pdf bib
Contextual Spelling Correction Using Latent Semantic Analysis
Michael P. Jones | James H. Martin
Fifth Conference on Applied Natural Language Processing