Word Embeddings for the Construction Domain
This provides domain-specific word embeddings for construction NLP applications, though it is incremental as it applies an existing method to new data.
The authors created construction-specific word embeddings by training word2vec on an 11M-word corpus they compiled from online sources, and showed these embeddings capture domain concepts and outperform Google News embeddings in an injury report classification task while enabling faster processing with minimal performance loss.
We introduce word vectors for the construction domain. Our vectors were obtained by running word2vec on an 11M-word corpus that we created from scratch by leveraging freely-accessible online sources of construction-related text. We first explore the embedding space and show that our vectors capture meaningful construction-specific concepts. We then evaluate the performance of our vectors against that of ones trained on a 100B-word corpus (Google News) within the framework of an injury report classification task. Without any parameter tuning, our embeddings give competitive results, and outperform the Google News vectors in many cases. Using a keyword-based compression of the reports also leads to a significant speed-up with only a limited loss in performance. We release our corpus and the data set we created for the classification task as publicly available, in the hope that they will be used by future studies for benchmarking and building on our work.