An End-to-End Document-Level Neural Discourse Parser Exploiting Multi-Granularity Representations
This work provides a significant improvement in document-level discourse parsing for NLP researchers and applications requiring deep textual understanding, pushing the boundaries towards human-level performance.
This paper tackles the challenge of document-level discourse parsing using Rhetorical Structure Theory (RST). The authors propose an end-to-end encoder-decoder neural architecture that leverages multi-granularity representations from a pre-trained contextual language model, achieving state-of-the-art performance and approaching human-level accuracy on the benchmarked RST dataset.
Document-level discourse parsing, in accordance with the Rhetorical Structure Theory (RST), remains notoriously challenging. Challenges include the deep structure of document-level discourse trees, the requirement of subtle semantic judgments, and the lack of large-scale training corpora. To address such challenges, we propose to exploit robust representations derived from multiple levels of granularity across syntax and semantics, and in turn incorporate such representations in an end-to-end encoder-decoder neural architecture for more resourceful discourse processing. In particular, we first use a pre-trained contextual language model that embodies high-order and long-range dependency to enable finer-grain semantic, syntactic, and organizational representations. We further encode such representations with boundary and hierarchical information to obtain more refined modeling for document-level discourse processing. Experimental results show that our parser achieves the state-of-the-art performance, approaching human-level performance on the benchmarked RST dataset.