# Improve Discourse Dependency Parsing with Contextualized Representations

arXiv: https://arxiv.org/abs/2205.02090 · HTML: https://mlsanity.com/paper/2205.02090/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 4 May 2022.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues](https://mlsanity.com/paper/1812.00176/) (2018)
- [SciDTB: Discourse Dependency TreeBank for Scientific Abstracts](https://mlsanity.com/paper/1806.03653/) (2018)
- [Implicit Discourse Relation Identification for Open-domain Dialogues](https://mlsanity.com/paper/1907.03975/) (2019)
- [Unifying Discourse Resources with Dependency Framework](https://mlsanity.com/paper/2101.00167/) (2021)

## Built on by (most cited first, 1 of 1)

- [Improving Topic Segmentation by Injecting Discourse Dependencies](https://mlsanity.com/paper/2209.08626/) (2022)

## Abstract (arXiv)

Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and their relations to the context. In this paper, we propose to take advantage of transformers to encode contextualized representations of units of different levels to dynamically capture the information required for discourse dependency analysis on intra- and inter-sentential levels. Motivated by the observation of writing patterns commonly shared across articles, we propose a novel method that treats discourse relation identification as a sequence labelling task, which takes advantage of structural information from the context of extracted discourse trees, and substantially outperforms traditional direct-classification methods. Experiments show that our model achieves state-of-the-art results on both English and Chinese datasets.