# A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech

Source: [A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech](<https://www.sota2.com/research/paper/68fa6a231e209131cea26433>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:31:58.003Z

Authors: Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Nianwen Xue, Ji-Rong Wen

Published: 2021-06-07T05:22:37.000Z

## Abstract

In this paper, we present a neural model for joint dropped pronoun recovery (DPR) and conversational discourse parsing (CDP) in Chinese conversational speech. We show that DPR and CDP are closely related, and a joint model benefits both tasks. We refer to our model as DiscProReco, and it first encodes the tokens in each utterance in a conversation with a directed Graph Convolutional Network (GCN). The token states for an utterance are then aggregated to produce a single state for each utterance. The utterance states are then fed into a biaffine classifier to construct a conversational discourse graph. A second (multi-relational) GCN is then applied to the utterance states to produce a discourse relation-augmented representation for the utterances, which are then fused together with token states in each utterance as input to a dropped pronoun recovery layer. The joint model is trained and evaluated on a new Structure Parsing-enhanced Dropped Pronoun Recovery (SPDPR) dataset that we annotated with both two types of information. Experimental results on the SPDPR dataset and other benchmarks show that DiscProReco significantly outperforms the state-of-the-art baselines of both tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Dropped Pronoun Recovery on SPDPR (test)](<https://www.sota2.com/research/sota/dropped-pronoun-recovery-on-spdpr-test.md>): Dropped Pronoun Recovery; SPDPR (test); Precision: 61.13.

- [Conversational Discourse Parsing on STAC (test)](<https://www.sota2.com/research/sota/conversational-discourse-parsing-on-stac-test.md>): Conversational Discourse Parsing; STAC (test); Arc Score: 74.1.

- [Conversational Discourse Parsing on SPDPR (test)](<https://www.sota2.com/research/sota/conversational-discourse-parsing-on-spdpr-test.md>): Conversational Discourse Parsing; SPDPR (test); Arc Score: 87.97.

- [Dropped Pronoun Recovery on OntoNotes TC 5.0 (CoNLL 2012 Shared Task) (test)](<https://www.sota2.com/research/sota/dropped-pronoun-recovery-on-ontonotes-tc-5-0-conll-2012-shared-task-test.md>): Dropped Pronoun Recovery; OntoNotes TC 5.0 (CoNLL 2012 Shared Task) (test); Precision: 0.4462.

- [Dropped Pronoun Recovery on BaiduZhidao (test)](<https://www.sota2.com/research/sota/dropped-pronoun-recovery-on-baiduzhidao-test.md>): Dropped Pronoun Recovery; BaiduZhidao (test); Precision: 47.31.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.03345>)

[PDF](<https://arxiv.org/pdf/2106.03345.pdf>)

[Implementation](<https://github.com/ningningyang/DiscProReco>)