# Biaffine Discourse Dependency Parsing

arXiv: https://arxiv.org/abs/2201.04450 · HTML: https://mlsanity.com/paper/2201.04450/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 12 Jan 2022.

## Builds on (most cited first, 7 of 7)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations](https://mlsanity.com/paper/1603.04351/) (2016)
- [Efficient Second-Order TreeCRF for Neural Dependency Parsing](https://mlsanity.com/paper/2005.00975/) (2020)
- [Neural Discourse Structure for Text Categorization](https://mlsanity.com/paper/1702.01829/) (2017)
- [SciDTB: Discourse Dependency TreeBank for Scientific Abstracts](https://mlsanity.com/paper/1806.03653/) (2018)
- [Evaluating Discourse in Structured Text Representations](https://mlsanity.com/paper/1906.01472/) (2019)

## Abstract (arXiv)

We provide a study of using the biaffine model for neural discourse dependency parsing and achieve significant performance improvement compared with the baseline parsers. We compare the Eisner algorithm and the Chu-Liu-Edmonds algorithm in the task and find that using the Chu-Liu-Edmonds algorithm generates deeper trees and achieves better performance. We also evaluate the structure of the output of the parser with average maximum path length and average proportion of leaf nodes and find that the dependency trees generated by the parser are close to the gold trees. As the corpus allows non-projective structures, we analyze the complexity of non-projectivity of the corpus and find that the dependency structures in this corpus have gap degree at most one and edge degree at most one.