Sentence encoders, which produce sentence embeddings using neural networks, are typically evaluated by how well they transfer to downstream tasks. This includes semantic similarity, an important task in natural language understanding. Although there has been much work dedicated to building sentence encoders, the accompanying transfer learning techniques have received relatively little attention. In this paper, we propose a transfer learning setting specialized for semantic similarity, which we refer to as direct network transfer. Through experiments on several standard text similarity datasets, we show that applying direct network transfer to existing encoders can lead to state-of-the-art performance. Additionally, we compare several approaches to transfer sentence encoders to semantic similarity tasks, showing that the choice of transfer learning setting greatly affects the performance in many cases, and differs by encoder and dataset.
View on arXiv