A Hierarchical Transformer for Unsupervised Parsing
This addresses the challenge of incorporating hierarchical structure into language models for improved linguistic tasks, though it is incremental as it adapts existing mechanisms.
The paper tackles the problem of enabling transformer models to learn hierarchical representations for natural language, achieving an F1-score of about 50% on unsupervised parsing using the WSJ10 dataset.
The underlying structure of natural language is hierarchical; words combine into phrases, which in turn form clauses. An awareness of this hierarchical structure can aid machine learning models in performing many linguistic tasks. However, most such models just process text sequentially and there is no bias towards learning hierarchical structure encoded into their architecture. In this paper, we extend the recent transformer model (Vaswani et al., 2017) by enabling it to learn hierarchical representations. To achieve this, we adapt the ordering mechanism introduced in Shen et al., 2018, to the self-attention module of the transformer architecture. We train our new model on language modelling and then apply it to the task of unsupervised parsing. We achieve reasonable results on the freely available subset of the WSJ10 dataset with an F1-score of about 50%.