Multi-Context Term Embeddings: the Use Case of Corpus-based Term Set Expansion
This work addresses term set expansion for natural language processing applications, but it is incremental as it builds on existing embedding methods with a new classifier and dataset.
The paper tackles the problem of corpus-based term set expansion by introducing a novel algorithm that combines multi-context term embeddings with a neural classifier, achieving up to a 5-point improvement in mean average precision over the best baseline on a new dataset.
In this paper, we present a novel algorithm that combines multi-context term embeddings using a neural classifier and we test this approach on the use case of corpus-based term set expansion. In addition, we present a novel and unique dataset for intrinsic evaluation of corpus-based term set expansion algorithms. We show that, over this dataset, our algorithm provides up to 5 mean average precision points over the best baseline.