Assessing incrementality in sequence-to-sequence models
This work addresses the cognitive plausibility of attention mechanisms in computational linguistics, which is an incremental improvement in model analysis.
The paper tackled the problem of assessing incrementality in sequence-to-sequence models, particularly comparing RNNs with and without attention mechanisms, and identified key differences in their sentence processing behaviors.
Since their inception, encoder-decoder models have successfully been applied to a wide array of problems in computational linguistics. The most recent successes are predominantly due to the use of different variations of attention mechanisms, but their cognitive plausibility is questionable. In particular, because past representations can be revisited at any point in time, attention-centric methods seem to lack an incentive to build up incrementally more informative representations of incoming sentences. This way of processing stands in stark contrast with the way in which humans are believed to process language: continuously and rapidly integrating new information as it is encountered. In this work, we propose three novel metrics to assess the behavior of RNNs with and without an attention mechanism and identify key differences in the way the different model types process sentences.