Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levels
This work addresses the challenge of automatically acquiring insights into word-sentence links in natural language processing, with incremental improvements in multi-level classification.
The authors tackled the problem of linking hierarchical linguistic components in text classification by designing a deep neural network architecture that wires lower and higher levels, resulting in MHAL outperforming equivalent models without compositional incentives and enabling zero-shot word-level tasks.
In natural languages, words are used in association to construct sentences. It is not words in isolation, but the appropriate combination of hierarchical structures that conveys the meaning of the whole sentence. Neural networks can capture expressive language features; however, insights into the link between words and sentences are difficult to acquire automatically. In this work, we design a deep neural network architecture that explicitly wires lower and higher linguistic components; we then evaluate its ability to perform the same task at different hierarchical levels. Settling on broad text classification tasks, we show that our model, MHAL, learns to simultaneously solve them at different levels of granularity by fluidly transferring knowledge between hierarchies. Using a multi-head attention mechanism to tie the representations between single words and full sentences, MHAL systematically outperforms equivalent models that are not incentivized towards developing compositional representations. Moreover, we demonstrate that, with the proposed architecture, the sentence information flows naturally to individual words, allowing the model to behave like a sequence labeller (which is a lower, word-level task) even without any word supervision, in a zero-shot fashion.