Unsupervised Neural Aspect Search with Related Terms Extraction
This addresses the challenge of extracting aspect-term pairs without labeled data for NLP applications, though it appears incremental as it builds on existing unsupervised methods.
The paper tackles the problem of unsupervised aspect identification and term extraction in NLP, particularly in multi-aspect settings, by proposing a novel neural network with a convolutional multi-attention mechanism and a special loss function, resulting in improved precision on a real-world dataset.
The tasks of aspect identification and term extraction remain challenging in natural language processing. While supervised methods achieve high scores, it is hard to use them in real-world applications due to the lack of labelled datasets. Unsupervised approaches outperform these methods on several tasks, but it is still a challenge to extract both an aspect and a corresponding term, particularly in the multi-aspect setting. In this work, we present a novel unsupervised neural network with convolutional multi-attention mechanism, that allows extracting pairs (aspect, term) simultaneously, and demonstrate the effectiveness on the real-world dataset. We apply a special loss aimed to improve the quality of multi-aspect extraction. The experimental study demonstrates, what with this loss we increase the precision not only on this joint setting but also on aspect prediction only.