Multi-Label Transfer Learning for Multi-Relational Semantic Similarity
This addresses the need for more efficient and accurate multi-relational semantic similarity systems, though it is incremental as it builds on existing LSTM and transfer learning techniques.
The paper tackles the problem of predicting multiple semantic relations between short texts simultaneously, proposing a multi-label transfer learning approach that outperforms single-task and traditional multi-task methods, achieving state-of-the-art performance on most relations in the Human Activity Phrase dataset.
Multi-relational semantic similarity datasets define the semantic relations between two short texts in multiple ways, e.g., similarity, relatedness, and so on. Yet, all the systems to date designed to capture such relations target one relation at a time. We propose a multi-label transfer learning approach based on LSTM to make predictions for several relations simultaneously and aggregate the losses to update the parameters. This multi-label regression approach jointly learns the information provided by the multiple relations, rather than treating them as separate tasks. Not only does this approach outperform the single-task approach and the traditional multi-task learning approach, but it also achieves state-of-the-art performance on all but one relation of the Human Activity Phrase dataset.